© 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. 168634
    Prev
    Next
    INDEX
    Explanations

    current density or repairs

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

    decisions or instructions

    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
     a
    0.51
     delinquent
    0.50
     potentially
    0.48
     Somalia
    0.48
     Angola
    0.48
     riot
    0.48
     marketing
    0.47
    тернет
    0.47
     marijuana
    0.47
     decarbon
    0.46
    POSITIVE LOGITS
     훨
    0.56
    훨
    0.55
     최고의
    0.51
    lacht
    0.48
    satz
    0.47
    avoid
    0.47
     不需要
    0.46
    thebetter
    0.46
     Toutefois
    0.46
    menin
    0.45
    Activations Density 0.001%

    No Known Activations