© 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. 18463
    Prev
    Next
    INDEX
    Explanations

    addresses and locations

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

    map links and addresses

    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
    镙
    0.41
    RENDITION
    0.40
    стю
    0.39
    COX
    0.39
     titer
    0.38
    뭡
    0.38
    အား
    0.37
    NeedConnect
    0.37
    裵
    0.37
     renew
    0.37
    POSITIVE LOGITS
     https
    0.50
    https
    0.49
     domingo
    0.49
    📍
    0.46
     Restaurant
    0.45
     Conservatory
    0.45
    āv
    0.45
     Sundays
    0.43
    〒
    0.43
     Settlement
    0.43
    Activations Density 0.028%

    No Known Activations