© 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. 156642
    Prev
    Next
    INDEX
    Explanations

    location:

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

    counting years

    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
     opponent
    0.47
     receptor
    0.46
     pett
    0.46
     کرے
    0.45
     laboral
    0.45
     dla
    0.45
     oppon
    0.45
    ඡ
    0.44
     sulla
    0.44
     compat
    0.44
    POSITIVE LOGITS
    разу
    0.52
    гры
    0.50
    Minimal
    0.50
    Compounds
    0.50
    Dataset
    0.49
    Sem
    0.49
    Disease
    0.49
    жала
    0.49
    Neces
    0.49
    Assessment
    0.48
    Activations Density 0.010%

    No Known Activations