© 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. 222437
    Prev
    Next
    INDEX
    Explanations

    leather, marriage, dating, car, strap

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

    reading comprehension

    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
    हम
    0.51
    UN
    0.48
    Tra
    0.48
    א
    0.47
    irti
    0.46
    חי
    0.46
    Trail
    0.45
    안
    0.45
    Estamos
    0.44
    ח
    0.44
    POSITIVE LOGITS
     suede
    0.50
    、
    0.50
     surged
    0.46
     smothered
    0.45
     cyclones
    0.44
     auffi
    0.44
     rebounded
    0.44
     sensual
    0.42
     mousse
    0.42
     customizable
    0.41
    Activations Density 0.001%

    No Known Activations