© 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. 134863
    Prev
    Next
    INDEX
    Explanations

    understanding choices and specific details

    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
     Emmett
    0.46
    Em
    0.44
    来说
    0.44
    养
    0.44
     соответственно
    0.43
    း
    0.43
     enriching
    0.43
     シェ
    0.42
     సమ
    0.41
     sû
    0.41
    POSITIVE LOGITS
    umd
    0.55
    ança
    0.54
     string
    0.51
    ungen
    0.49
    禱
    0.47
     footballer
    0.47
    al
    0.46
    ighet
    0.46
    बॉक्स
    0.46
    id
    0.46
    Activations Density 0.001%

    No Known Activations