© 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. 182392
    Prev
    Next
    INDEX
    Explanations

    government, corporate, or specific entities

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

    be followed by positive attributes

    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
    ר
    0.55
    Dentro
    0.54
    Während
    0.53
    ри
    0.52
    Მ
    0.50
    瀋
    0.50
    ל
    0.49
    פר
    0.49
    პერ
    0.49
    சே
    0.49
    POSITIVE LOGITS
     instituto
    0.44
     United
    0.44
     olvid
    0.43
     government
    0.43
     sill
    0.43
     Darryl
    0.42
    united
    0.42
     govt
    0.41
     postpaid
    0.41
    aci
    0.41
    Activations Density 0.000%

    No Known Activations