© 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. 168107
    Prev
    Next
    INDEX
    Explanations

    Midnight Silver premium

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

    international concepts and terms

    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
    .",
    0.50
     dimanche
    0.50
    -
    0.50
     twentieth
    0.50
    ,
    0.49
     industry
    0.49
     by
    0.47
     annually
    0.47
     czerwca
    0.46
     because
    0.45
    POSITIVE LOGITS
     relleno
    0.49
    uslararası
    0.49
     रेसिपी
    0.48
    蕾
    0.45
    睜
    0.44
    あなたの
    0.44
     پخش
    0.44
    你的
    0.43
     Ambient
    0.43
    周辺
    0.43
    Activations Density 0.000%

    No Known Activations