© 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. 225171
    Prev
    Next
    INDEX
    Explanations

    Starting words for lists or specific contexts

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

    assumes you

    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
     welche
    0.47
     gemeinsam
    0.47
    밂
    0.46
     analogs
    0.46
     gewesen
    0.46
    opolitan
    0.45
     Akademie
    0.44
    altering
    0.44
    ovatel
    0.44
     deoarece
    0.44
    POSITIVE LOGITS
    ระยะ
    0.45
    </h4>
    0.44
     disappoint
    0.44
    உ
    0.44
    蜜
    0.43
    ↵
    0.43
    ️
    0.43
     क्रिप्टो
    0.43
     activos
    0.43
     SOUND
    0.42
    Activations Density 0.000%

    No Known Activations