© 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. 145190
    Prev
    Next
    INDEX
    Explanations

    booking and playing

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

    mentions of specific items preceded by list markers

    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
     desirability
    0.47
    钦
    0.47
    可以
    0.47
     magaz
    0.46
    ﺽ
    0.46
    λλά
    0.45
    顗
    0.45
    线性
    0.45
    书记
    0.45
    يذ
    0.44
    POSITIVE LOGITS
    arks
    0.58
    oks
    0.53
    umal
    0.53
    oue
    0.53
    ul
    0.52
    arsi
    0.52
    unu
    0.52
    oji
    0.51
    oux
    0.51
    ka
    0.50
    Activations Density 0.000%

    No Known Activations