© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221378
    Prev
    Next
    INDEX
    Explanations

    seen or saw context

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

    system queries and responses

    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
    in
    0.47
    iana
    0.46
    name
    0.45
    capital
    0.45
    and
    0.44
    family
    0.44
    andang
    0.44
    </strong>
    0.43
    ma
    0.43
    mult
    0.42
    POSITIVE LOGITS
    𝜁
    0.56
     Joystick
    0.55
     vélo
    0.52
     moteurs
    0.50
     Synchronization
    0.48
     contrôler
    0.48
     Laplacian
    0.48
     gamepad
    0.47
     véhicules
    0.47
     झटका
    0.46
    Activations Density 0.000%

    No Known Activations