© 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. 72231
    Prev
    Next
    INDEX
    Explanations

    awards, roles, and issues

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

    sophisticated predictive text engine

    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
    ↵↵
    0.49
     term
    0.40
    Sci
    0.40
    ៅ
    0.39
    ?
    0.38
    '
    0.38
    馬
    0.37
     uw
    0.37
    hydrate
    0.37
    語
    0.37
    POSITIVE LOGITS
    nements
    0.59
    :<
    0.54
     wartość
    0.54
    یط
    0.52
    тков
    0.52
     halved
    0.52
    垐
    0.52
     nieruchomości
    0.51
    𝓭
    0.51
     MODELS
    0.49
    Activations Density 0.000%

    No Known Activations