© 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. 149452
    Prev
    Next
    INDEX
    Explanations

    charge, defence, murder

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

    specifications, facts, or calculations

    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
    на
    0.54
    Comput
    0.52
    వె
    0.52
    C
    0.52
     нега
    0.49
    па
    0.49
    а
    0.49
    離婚
    0.48
    Whatsapp
    0.48
    γ
    0.48
    POSITIVE LOGITS
     AMG
    0.48
     SOAP
    0.45
     konsult
    0.45
     Sandberg
    0.44
     Potomac
    0.44
     inaugur
    0.42
     CRM
    0.42
     Hoffman
    0.42
     relatório
    0.42
     placebo
    0.42
    Activations Density 0.001%

    No Known Activations