© 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. 23031
    Prev
    Next
    INDEX
    Explanations

    permission context

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

    permission issues

    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
     it
    0.76
    t
    0.74
    a
    0.68
     be
    0.65
    c
    0.64
     legumes
    0.63
    i
    0.63
     идеи
    0.63
     riesgos
    0.62
    '
    0.61
    POSITIVE LOGITS
    ↵↵
    0.88
    ти
    0.66
    0.64
    ल
    0.62
    to
    0.62
    م
    0.60
    ↵↵↵
    0.59
     to
    0.59
    ATING
    0.59
    oc
    0.58
    Activations Density 0.002%

    No Known Activations