© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109986
    Prev
    Next
    INDEX
    Explanations

    lists of items or concepts

    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
     filtre
    0.54
    珽
    0.48
    ﾄ
    0.45
     seam
    0.42
    ਿਹ
    0.41
     convolution
    0.41
     stitch
    0.41
     told
    0.40
    ראה
    0.40
    र
    0.40
    POSITIVE LOGITS
    ;
    0.53
    一
    0.49
    م
    0.47
    স্ব
    0.46
     Money
    0.46
     Gamble
    0.44
     ശബരിമല
    0.43
     nhá
    0.43
    ні
    0.42
    鹜
    0.42
    Activations Density 0.001%

    No Known Activations