© 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. 32169
    Prev
    Next
    INDEX
    Explanations

    serial clock and

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

    command-line interface, pathways, and conjunctions

    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
    떳
    0.41
    ㅈ
    0.41
    ಿನಿ
    0.41
     persistently
    0.41
     presentato
    0.41
     publicado
    0.40
     pubblicato
    0.40
     proactively
    0.40
     vigorously
    0.39
     scelto
    0.39
    POSITIVE LOGITS
     và
    0.54
     verschied
    0.46
     மற்றும்
    0.46
     और
    0.45
     Textiles
    0.45
     ও
    0.44
     Raceway
    0.44
     çeşitli
    0.43
     Berber
    0.43
     և
    0.43
    Activations Density 0.000%

    No Known Activations