© 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. 57351
    Prev
    Next
    INDEX
    Explanations

    political leaders or royalty

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

    president of

    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
     identiques
    0.69
    كثر
    0.64
     iguales
    0.64
     apporte
    0.64
     dominante
    0.63
     sarees
    0.62
     cír
    0.61
    %)
    0.60
    ل
    0.59
     الس
    0.59
    POSITIVE LOGITS
    ’
    0.78
    ial
    0.56
    itter
    0.54
    ick
    0.54
    ider
    0.54
    for
    0.53
    hip
    0.53
    land
    0.53
    let
    0.52
    por
    0.52
    Activations Density 0.037%

    No Known Activations