© 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. 241953
    Prev
    Next
    INDEX
    Explanations

    rules, criteria, and actions

    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
     Tonawanda
    0.46
     $\{
    0.46
     ото
    0.45
    сто
    0.44
    ня
    0.44
    ходя
    0.44
    datatables
    0.44
     lined
    0.43
    ütün
    0.42
     вести
    0.42
    POSITIVE LOGITS
     RULE
    0.56
    是
    0.50
    ExpireTime
    0.47
    RULE
    0.46
     جوړونکي
    0.46
    SampleSize
    0.45
     FINAL
    0.45
    ovi
    0.45
    MediaPath
    0.44
     rule
    0.43
    Activations Density 0.001%

    No Known Activations