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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8750
    Prev
    Next
    INDEX
    Explanations

    telomere, telophase, Tel Aviv

    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_262k_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
    ments
    2.23
    ッド
    2.20
    THING
    2.03
     railroads
    1.99
    y
    1.96
    י
    1.86
    e
    1.85
    yim
    1.83
    கிறது
    1.82
    ettha
    1.82
    POSITIVE LOGITS
    ية
    2.00
    éfonos
    1.98
    ę
    1.95
    лен
    1.91
    მწიფ
    1.91
    에
    1.88
    Ẳ
    1.84
    х
    1.84
    вая
    1.83
    су
    1.82
    Activations Density 0.002%

    No Known Activations