© 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. 194616
    Prev
    Next
    INDEX
    Explanations

    guard at, first Thursday, further examination

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

    safety and profit

    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
     admi
    0.51
    斩
    0.50
    ﻡ
    0.49
    宰
    0.46
     ALSO
    0.46
    ulata
    0.46
    autorisation
    0.46
    وضوع
    0.46
    itura
    0.46
    核
    0.45
    POSITIVE LOGITS
     சிறந்த
    0.45
     seriousness
    0.45
     комфор
    0.43
     quantifiable
    0.43
     оцен
    0.42
     road
    0.42
     спор
    0.42
     temperat
    0.42
     civilized
    0.41
     못
    0.41
    Activations Density 0.000%

    No Known Activations