© 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. 11415
    Prev
    Next
    INDEX
    Explanations

    references and notes

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

    categorized breakdown

    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
     المقد
    0.42
    classlist
    0.41
     regressions
    0.41
    WEATHER
    0.40
    圣
    0.40
     pointB
    0.40
    SEVERE
    0.40
    িবাস
    0.40
     besta
    0.39
     halus
    0.39
    POSITIVE LOGITS
    <table>
    0.78
    </td>
    0.39
     '
    0.39
     MCT
    0.39
    ро
    0.38
    ần
    0.38
     Iconic
    0.38
     Moderator
    0.38
     Province
    0.38
     Table
    0.38
    Activations Density 0.017%

    No Known Activations