© 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. 41113
    Prev
    Next
    INDEX
    Explanations

    booking in advance

    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
    akaranam
    0.47
    conex
    0.47
    freund
    0.46
    листы
    0.46
    ಬೇಕು
    0.46
    켄
    0.46
    ியின்
    0.45
    lewati
    0.45
    냔
    0.45
    Также
    0.45
    POSITIVE LOGITS
     Cryptocurrency
    0.50
     Microscopy
    0.48
     Micro
    0.47
     trabalh
    0.46
     Chinese
    0.45
     Crypto
    0.45
     Light
    0.45
     MICRO
    0.45
     crypto
    0.44
     poor
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.