© 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. 57263
    Prev
    Next
    INDEX
    Explanations

    the company

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

    Even after, adopted, generates, example, often

    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
     representa
    0.52
     characteristics
    0.49
     evaluating
    0.47
     $\
    0.46
     triplets
    0.46
     appr
    0.46
     bets
    0.44
     altitudes
    0.44
     absolv
    0.44
     cautions
    0.44
    POSITIVE LOGITS
    υτό
    0.47
    hôtel
    0.46
    प्पू
    0.45
    cadilly
    0.45
    肚
    0.45
     গেলেন
    0.45
    uzzo
    0.44
     później
    0.43
    uzz
    0.42
     után
    0.42
    Activations Density 0.000%

    No Known Activations