© 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. 111306
    Prev
    Next
    INDEX
    Explanations

    furnish facilities

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

    describing relationships of things

    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
    abbr
    0.47
    거나
    0.45
    Volkswagen
    0.45
    ዎ
    0.45
    velles
    0.43
     همچنین
    0.43
    mnf
    0.42
    <unused1848>
    0.42
    Categorie
    0.42
    FileInputExcel
    0.42
    POSITIVE LOGITS
     HNO
    0.47
     τὴν
    0.45
     Receivable
    0.45
     deberá
    0.43
     ELECTRO
    0.43
     耐
    0.42
     innego
    0.42
     siguió
    0.41
     was
    0.40
     necesitaba
    0.40
    Activations Density 0.001%

    No Known Activations