© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101397
    Prev
    Next
    INDEX
    Explanations

    legal and physical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite

    specific items and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.68
     C
    0.62
    ’
    0.58
     V
    0.57
     may
    0.57
     I
    0.56
     from
    0.56
     O
    0.56
     S
    0.56
     May
    0.52
    POSITIVE LOGITS
    сці
    0.62
    핳
    0.57
     Förderung
    0.52
    jsdel
    0.52
     задач
    0.51
    ༢
    0.51
     ஜீய
    0.49
    wiąz
    0.49
     সম্পূর্ন
    0.49
    jhelp
    0.49
    Activations Density 0.000%

    No Known Activations