© 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. 144749
    Prev
    Next
    INDEX
    Explanations

    describing object or purpose

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

    quickly realized, legal action, game elements

    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
     islam
    0.56
    ایط
    0.53
    庾
    0.50
    済
    0.49
     diperlukan
    0.49
     islamic
    0.49
    酺
    0.49
    CHREIB
    0.49
     légales
    0.48
    误差
    0.48
    POSITIVE LOGITS
    re
    0.50
    n
    0.50
    fully
    0.48
    ere
    0.47
    e
    0.46
    fe
    0.45
    t
    0.45
    g
    0.45
    ;
    0.45
    h
    0.44
    Activations Density 0.001%

    No Known Activations