© 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. 24398
    Prev
    Next
    INDEX
    Explanations

    linkedin and email contexts

    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
    Methylsulfanyl
    0.61
    ^+,
    0.61
     rétrécies
    0.55
    <unused50>
    0.55
     ಆಧ
    0.55
    Pyrazole
    0.55
     катастро
    0.54
     তাতে
    0.54
     त्रिपाठी
    0.53
    segaretro
    0.53
    POSITIVE LOGITS
    ت
    0.82
    a
    0.71
    l
    0.71
    t
    0.66
    ل
    0.65
    ini
    0.65
     U
    0.64
     Table
    0.64
     You
    0.63
     Bruce
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.