© 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. 244992
    Prev
    Next
    INDEX
    Explanations

    new project of

    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
    d
    0.64
    e
    0.57
    is
    0.56
    a
    0.52
    b
    0.50
    ma
    0.49
    IS
    0.48
    y
    0.48
    ta
    0.48
    9
    0.47
    POSITIVE LOGITS
    ﮐ
    0.52
     smuggled
    0.50
     پار
    0.49
     ਜ
    0.49
     sintomi
    0.49
     コットン
    0.48
     parall
    0.47
     przech
    0.47
     îles
    0.46
     sown
    0.46
    Activations Density 0.001%

    No Known Activations