© 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. 84806
    Prev
    Next
    INDEX
    Explanations

    describing situations and states

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

    block or allow

    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
    Choisissez
    0.50
    Х
    0.48
    Chris
    0.48
     alguns
    0.46
     moviment
    0.46
     mouvement
    0.45
     anaer
    0.45
     abrog
    0.44
     ambivalent
    0.44
     moverse
    0.43
    POSITIVE LOGITS
     Evil
    0.45
     More
    0.45
    า
    0.45
    atari
    0.45
     Warfare
    0.44
    quard
    0.44
    ARTI
    0.43
    дови
    0.42
     Last
    0.42
     Simple
    0.41
    Activations Density 0.002%

    No Known Activations