© 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. 189726
    Prev
    Next
    INDEX
    Explanations

    concepts and specific fields

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

    `-print0` option

    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
    THA
    0.52
    म
    0.50
    TPR
    0.49
    ir
    0.46
    m
    0.46
    ز
    0.46
    IGNED
    0.45
    KET
    0.45
    يه
    0.44
    냉
    0.44
    POSITIVE LOGITS
     lettuce
    0.54
     peninsula
    0.54
     humanity
    0.53
     bureaucracy
    0.52
     food
    0.52
     gynec
    0.51
     civilian
    0.50
     solidarity
    0.50
     taxonom
    0.50
     synagogue
    0.50
    Activations Density 0.000%

    No Known Activations