© 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. 233297
    Prev
    Next
    INDEX
    Explanations

    roast, crisis, Baptist

    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
    avail
    0.45
    duplicated
    0.45
    ।
    0.45
     applaud
    0.44
     suscit
    0.43
     utilising
    0.41
     ।
    0.40
    odils
    0.39
    缚
    0.39
    evening
    0.39
    POSITIVE LOGITS
    Estamos
    0.48
     Formul
    0.47
    рал
    0.46
    各地
    0.45
     JFrame
    0.45
    րան
    0.44
    stvo
    0.43
    кому
    0.43
    हमने
    0.43
     ईमित्र
    0.43
    Activations Density 0.000%

    No Known Activations