© 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. 11139
    Prev
    Next
    INDEX
    Explanations

    lists or bullet points

    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
     refinance
    0.52
     referral
    0.50
     referrer
    0.49
     request
    0.48
     （
    0.47
     referrals
    0.47
     referee
    0.46
     individually
    0.46
     delegate
    0.44
     randomly
    0.43
    POSITIVE LOGITS
    労働
    0.56
     राउत
    0.54
    穰
    0.49
    á
    0.49
    ff
    0.49
     විය
    0.49
     урок
    0.48
    limegreen
    0.47
    radiative
    0.46
     منظر
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.