© 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. 234260
    Prev
    Next
    INDEX
    Explanations

    efficiency, economy, latest

    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
     normalen
    0.50
    跎
    0.49
    ณิต
    0.48
     Hb
    0.46
     plugins
    0.46
     gusto
    0.46
     skepticism
    0.45
     murmur
    0.45
     bis
    0.44
     plag
    0.44
    POSITIVE LOGITS
    c
    0.70
    t
    0.63
    members
    0.54
    s
    0.54
     خبری
    0.52
    ar
    0.51
    turkish
    0.51
    ceti
    0.49
    ro
    0.49
    d
    0.49
    Activations Density 0.000%

    No Known Activations