© 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. 101125
    Prev
    Next
    INDEX
    Explanations

    description of specific communities

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

    Tiber, slime blocks, societal adaptation

    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
    ล
    0.59
    ल
    0.54
    ड
    0.54
     मध्या
    0.54
     кукуру
    0.54
    लया
    0.52
    ቿ
    0.52
    ޫ
    0.50
    🥔
    0.50
    🍙
    0.50
    POSITIVE LOGITS
     Royaume
    0.47
     Village
    0.46
     Antilles
    0.46
     Wu
    0.45
     orthogonal
    0.45
     König
    0.45
     Spokane
    0.45
     village
    0.45
     Episcopal
    0.43
     corrente
    0.43
    Activations Density 0.001%

    No Known Activations