© 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. 21545
    Prev
    Next
    INDEX
    Explanations

    with relatives

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

    level of concern or interest

    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
    such
    0.54
    messer
    0.52
    Dentro
    0.48
    ת
    0.47
    Todas
    0.46
    נטי
    0.46
    noble
    0.46
    ב
    0.45
    і
    0.45
    Sterling
    0.45
    POSITIVE LOGITS
     tờ
    0.54
     zmniejs
    0.52
     склон
    0.51
     wobec
    0.50
     percep
    0.50
     heuristics
    0.49
     Reduces
    0.49
     possibilité
    0.49
    pengaruhi
    0.49
     уров
    0.49
    Activations Density 0.000%

    No Known Activations