© 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. 143083
    Prev
    Next
    INDEX
    Explanations

    completed yet tasks

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

    permissions, principal, pressures, fragments

    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
    成像
    0.46
     보안
    0.44
    PERTIES
    0.44
    音が
    0.44
    導演
    0.43
    墳
    0.43
    ુંદર
    0.43
     tumours
    0.42
    车载
    0.42
    ཤ
    0.42
    POSITIVE LOGITS
    ()
    0.52
     wasn
    0.50
    for
    0.48
     for
    0.48
     Equality
    0.47
     było
    0.46
     Domin
    0.45
     was
    0.45
    Equality
    0.45
     literally
    0.45
    Activations Density 0.002%

    No Known Activations