© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 137071
    Prev
    Next
    INDEX
    Explanations

    were living, become part, find what, hurt

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

    descriptive words

    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
    ringen
    0.50
    ﺭ
    0.49
    “.
    0.49
     команда
    0.49
    psie
    0.49
     جري
    0.48
    athy
    0.47
    arthy
    0.46
    rians
    0.46
    Rita
    0.46
    POSITIVE LOGITS
     ofere
    0.52
     kõr
    0.48
    毎回
    0.48
     of
    0.47
    Y
    0.45
    ブラ
    0.44
    え
    0.44
    化
    0.44
     bao
    0.44
     của
    0.44
    Activations Density 0.000%

    No Known Activations