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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63694
    Prev
    Next
    INDEX
    Explanations

    changes and corrections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
    ですし
    0.48
     এটাই
    0.40
    abble
    0.39
     Поэтому
    0.38
    ضي
    0.38
     Тогда
    0.38
     ខ
    0.38
    諰
    0.38
     பார்க்கும்
    0.37
     проводят
    0.37
    POSITIVE LOGITS
    改为
    0.85
    改成
    0.84
    变成
    0.82
    變成
    0.80
    变成了
    0.77
    转化为
    0.68
    变为
    0.66
     becomes
    0.64
    转换为
    0.63
     instead
    0.60
    Activations Density 0.099%

    No Known Activations