© 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. 86035
    Prev
    Next
    INDEX
    Explanations

    proper nouns and place names

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

    human states and experiences

    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
     관련
    0.57
    your
    0.48
    related
    0.47
    DEP
    0.47
     שלך
    0.46
    你的
    0.46
    బడు
    0.46
    ⏹
    0.45
    као
    0.45
    வியல்
    0.45
    POSITIVE LOGITS
     Hester
    0.49
     clientele
    0.49
     Besançon
    0.48
     nữ
    0.48
     Hug
    0.47
    leigh
    0.46
     Paris
    0.45
     Parisian
    0.45
     Groningen
    0.45
     ludzi
    0.44
    Activations Density 0.000%

    No Known Activations