© 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. 162175
    Prev
    Next
    INDEX
    Explanations

    winning singer

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

    Information Owners

    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
    底
    0.48
    锟
    0.46
    ьа
    0.46
    ดัง
    0.45
    affer
    0.45
    анд
    0.44
    h
    0.44
    Dun
    0.44
    ON
    0.43
    elt
    0.43
    POSITIVE LOGITS
     İm
    0.45
     Boliv
    0.45
    鯵
    0.44
    ッセ
    0.44
    ွေး
    0.43
     Crimean
    0.42
     Aziz
    0.42
     recharging
    0.42
     Antip
    0.41
     તમને
    0.41
    Activations Density 0.001%

    No Known Activations