© 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. 53635
    Prev
    Next
    INDEX
    Explanations

    fraudulent intellectualspersonal piecefree revolutioninspired designs

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

    very [adjective] question

    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
     inset
    0.46
     estrange
    0.45
     decorate
    0.45
     promote
    0.45
     muffin
    0.44
     commemorate
    0.42
    ;*/
    0.42
    ри
    0.42
     plaatsen
    0.41
     avenge
    0.41
    POSITIVE LOGITS
     обши
    0.48
    CAT
    0.48
    quin
    0.48
    IS
    0.47
    laboratory
    0.46
    HAV
    0.46
    J
    0.46
    VAN
    0.45
    ıs
    0.44
    CAR
    0.44
    Activations Density 0.002%

    No Known Activations