© 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. 177456
    Prev
    Next
    INDEX
    Explanations

    offers, extras, coupons, or rates

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

    officially recognized geographic locations

    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
    தமிழ்
    0.46
    сят
    0.44
    ཥ
    0.43
     handsets
    0.43
    谒
    0.43
    jte
    0.42
    стной
    0.42
     वंदे
    0.42
    டக
    0.42
    ข้าว
    0.41
    POSITIVE LOGITS
     à
    0.48
     천
    0.47
     خص
    0.46
     MA
    0.45
    '
    0.45
    à
    0.45
     mentored
    0.44
     ennen
    0.44
     अग्र
    0.44
    เ
    0.43
    Activations Density 0.001%

    No Known Activations