© 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. 157817
    Prev
    Next
    INDEX
    Explanations

    domains, property, law

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

    urge you to reconsider

    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
     x
    0.55
     Follow
    0.47
     tangerine
    0.45
     ves
    0.44
     follow
    0.42
     d
    0.42
     as
    0.42
    Ⅱ
    0.42
     ham
    0.42
     Diagnose
    0.41
    POSITIVE LOGITS
     sueños
    0.53
     rêves
    0.52
    স্টে
    0.49
     satın
    0.49
    ężczy
    0.48
     необхідно
    0.47
    ztat
    0.46
    Bước
    0.46
    Été
    0.46
    Ecco
    0.46
    Activations Density 0.001%

    No Known Activations