© 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-262K
    7. 77666
    Prev
    Next
    INDEX
    Explanations

    GH doesn't, positions for, follow the, Why it

    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_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
     Wort
    0.43
     মহাশ
    0.43
     Minuten
    0.42
    *{
    0.42
     ornamental
    0.42
     ملازمت
    0.42
     단위
    0.42
     වශ
    0.41
     நிமிட
    0.41
     ہوئے۔
    0.41
    POSITIVE LOGITS
    ל
    0.54
    ल
    0.53
    टिंग
    0.48
    ह
    0.47
     auparavant
    0.46
    ोज़
    0.46
     converts
    0.46
    अफ
    0.45
    ル
    0.45
    خ
    0.45
    Activations Density 0.007%

    No Known Activations