© 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. 151792
    Prev
    Next
    INDEX
    Explanations

    contact details and topics

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

    Botox, Gemma, Trivia, Discussion

    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
    dua
    0.45
     ಮೆ
    0.43
    los
    0.42
    adion
    0.42
    adip
    0.42
    ordia
    0.42
    ২
    0.42
    restore
    0.41
    adora
    0.41
    མ
    0.41
    POSITIVE LOGITS
     Discussion
    0.54
     EMPLOY
    0.52
     चर्चा
    0.51
     Gespräch
    0.50
    Discussion
    0.50
     Introdu
    0.50
     CHAIRMAN
    0.50
    讨论
    0.49
     ERISA
    0.49
     oprac
    0.49
    Activations Density 0.001%

    No Known Activations