© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 2061
    Prev
    Next
    INDEX
    Explanations

    **TOP_ACTIVATING_TEXTS**: * "**April 2023**" * "**September 2021**" * "**June 28**" * "**February 1, 2024**" * "**October 26, 2023**" * "**June 5, 2024**" * "**May 5, 2024**" * "**September 4, 2021**" * "**July 23**" * "**May 16, 2024**"**Analysis**:The `MAX_ACTIVATING_TOKENS` list clearly contains months of the year (April, September, June, February, October, May, July).The `TOP_ACTIVATING_TEXTS` list confirms this by showing these months appearing within dates, often followed by years or days.months of the year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ین
    2.06
    ется
    1.77
    こと
    1.77
    Сто
    1.75
    ینگ
    1.64
    Зна
    1.59
    З
    1.59
    Те
    1.57
    Ста
    1.55
    Та
    1.55
    POSITIVE LOGITS
    speople
    1.80
    า
    1.77
    sigh
    1.71
    e
    1.66
    MAY
    1.55
     אף
    1.49
    tails
    1.47
    वर्ती
    1.45
    gherita
    1.45
    GOT
    1.44
    Activations Density 0.080%

    No Known Activations