© 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. 24389
    Prev
    Next
    INDEX
    Explanations

    likely to

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

    likely legal or humor

    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
     PDPN
    0.45
    괵
    0.45
     Pharmacology
    0.45
     Goose
    0.44
     Dolphin
    0.43
     STREAM
    0.43
     OutputStream
    0.42
     Ging
    0.41
    Databaze
    0.41
     Baume
    0.41
    POSITIVE LOGITS
    ,
    0.52
     быть
    0.50
     ambivalent
    0.49
     reprises
    0.49
     oxides
    0.48
     deadlines
    0.48
     شعر
    0.47
    ;
    0.47
     ambitions
    0.47
    ят
    0.46
    Activations Density 0.000%

    No Known Activations