© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 174472
    Prev
    Next
    INDEX
    Explanations

    economic or financial

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

    names and places

    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
    秣
    0.48
    вий
    0.46
    Begriff
    0.45
    чат
    0.45
    сит
    0.45
    Becker
    0.44
    ässig
    0.44
    či
    0.43
    ('>
    0.43
     '>
    0.42
    POSITIVE LOGITS
     Lounge
    0.46
     lounges
    0.46
    लिन
    0.45
     Theorems
    0.45
     экономических
    0.45
     thereafter
    0.44
     ekonom
    0.44
     экономической
    0.43
     Membranes
    0.43
     attributable
    0.42
    Activations Density 0.000%

    No Known Activations