© 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. 190468
    Prev
    Next
    INDEX
    Explanations

    phrases completing predictions or statements

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

    . or abbreviation

    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
    ﻵ
    0.49
     morti
    0.47
    해도
    0.47
    탄
    0.46
     కొన
    0.45
     dampers
    0.45
    _
    0.45
    ﺍ
    0.44
     mesons
    0.44
     muertos
    0.43
    POSITIVE LOGITS
    sehen
    0.48
    Citation
    0.47
    isch
    0.46
     நினைக்க
    0.46
    paralleled
    0.45
    citing
    0.45
    wss
    0.44
    Extreme
    0.44
    Invalid
    0.43
    ische
    0.43
    Activations Density 0.004%

    No Known Activations