© 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. 191573
    Prev
    Next
    INDEX
    Explanations

    `.` period, commas, and conjunctions

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

    years ago

    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
    த்து
    0.48
     Tiến
    0.46
    仡
    0.45
    त्तों
    0.45
    离子
    0.44
    氰
    0.44
    ஞ்
    0.44
    碘
    0.44
     Mech
    0.43
    setMax
    0.43
    POSITIVE LOGITS
     rupture
    0.46
     BOTTOM
    0.45
    /#
    0.44
     magnitude
    0.44
     rhetorical
    0.44
    /[
    0.43
    opar
    0.42
     ре
    0.42
     потрібно
    0.42
     रे
    0.42
    Activations Density 0.001%

    No Known Activations