© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 152150
    Prev
    Next
    INDEX
    Explanations

    run for sales

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

    testing the waters

    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
    )
    0.60
    ol
    0.49
    ,:)
    0.48
    forbidden
    0.48
    c
    0.48
    )~
    0.47
    punct
    0.47
    );
    0.46
    ंदा
    0.46
    henden
    0.46
    POSITIVE LOGITS
     ravine
    0.54
     திரு
    0.54
     ಸಂತ
    0.54
     salió
    0.53
     tap
    0.52
     came
    0.52
     ܠ
    0.52
     río
    0.50
     maintain
    0.48
     venido
    0.48
    Activations Density 0.001%

    No Known Activations