© 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. 44161
    Prev
    Next
    INDEX
    Explanations

    constructor arguments

    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
    id
    0.45
    引き続き
    0.44
     அவரின்
    0.40
    his
    0.37
    resizable
    0.36
     remind
    0.36
    o
    0.35
    Chinese
    0.35
    //
    0.35
    National
    0.34
    POSITIVE LOGITS
     टार
    0.46
     Déc
    0.46
     tule
    0.44
     இவ்வ
    0.43
    umping
    0.43
    úng
    0.41
     अफे
    0.41
     fæ
    0.41
     diese
    0.41
     embry
    0.40
    Activations Density 0.015%

    No Known Activations