© 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. 152532
    Prev
    Next
    INDEX
    Explanations

    roles and people types

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

    identifying advanced or nuanced concepts

    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
    魷
    0.45
    是由
    0.42
     자체가
    0.42
    があるので
    0.41
     consist
    0.40
     অনুমতি
    0.40
     состоит
    0.40
     що
    0.39
    ，
    0.39
    があり
    0.39
    POSITIVE LOGITS
     campañas
    0.46
    descripcion
    0.44
    ="|
    0.43
    described
    0.43
     campaña
    0.42
     décrites
    0.42
     habíamos
    0.41
     caractère
    0.41
     वर्णन
    0.40
     campagne
    0.40
    Activations Density 0.067%

    No Known Activations