© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3685
    Prev
    Next
    INDEX
    Explanations

    by or with followed by action/description

    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
    ądź
    0.99
     وعلى
    0.93
    enance
    0.84
    кновен
    0.82
     få
    0.82
    قاء
    0.81
    ์
    0.81
     éta
    0.80
    েও
    0.80
     ancak
    0.79
    POSITIVE LOGITS
     pastime
    0.85
    зак
    0.80
     haven
    0.77
    𝓈
    0.74
     cheers
    0.73
     rationally
    0.71
     hasn
    0.71
     lively
    0.71
    2
    0.70
     curve
    0.70
    Activations Density 0.103%

    No Known Activations