© 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. 251201
    Prev
    Next
    INDEX
    Explanations

    year, cash, nobody

    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
    єте
    0.53
    카
    0.50
     카
    0.47
    osz
    0.47
    __.
    0.45
    adip
    0.44
    sprintf
    0.44
    gie
    0.43
    ouvoir
    0.43
    oeste
    0.43
    POSITIVE LOGITS
     Hap
    0.48
     Mutation
    0.46
     и
    0.46
     Lapse
    0.45
     Trident
    0.45
     yaz
    0.44
     Britannia
    0.43
     Andreev
    0.42
     bằng
    0.42
     Jena
    0.41
    Activations Density 0.001%

    No Known Activations