© 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. 158188
    Prev
    Next
    INDEX
    Explanations

    older ago understand dismiss quality

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

    disallowed

    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
     incênd
    0.52
    郊
    0.51
    咫
    0.50
     mansions
    0.48
     hospitales
    0.47
     centaines
    0.46
     dominate
    0.46
     Flughafen
    0.46
     predominate
    0.45
    俯
    0.45
    POSITIVE LOGITS
    tokens
    0.48
    ativo
    0.48
     جسے
    0.45
     Noodles
    0.45
     আগে
    0.45
    キ
    0.43
     ہماری
    0.43
    🧒
    0.43
     assistant
    0.42
    Tokens
    0.42
    Activations Density 0.000%

    No Known Activations