© 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. 77521
    Prev
    Next
    INDEX
    Explanations

    health, summer, these

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

    zero trust

    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
     NaN
    0.51
     Unicode
    0.43
     ел
    0.43
     xl
    0.42
     |_{
    0.42
     참고
    0.41
    <code>
    0.41
     ET
    0.41
     Nature
    0.41
     এমনকি
    0.40
    POSITIVE LOGITS
    conto
    0.45
     yeux
    0.44
     فقد
    0.42
    mitglied
    0.42
     businesswoman
    0.40
    strateg
    0.39
    hombre
    0.39
    اء
    0.38
     eyewear
    0.38
     practic
    0.38
    Activations Density 0.000%

    No Known Activations