© 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. 128964
    Prev
    Next
    INDEX
    Explanations

    non-English words

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

    AMSI, arrays, service, intelligence, transaction, Stream

    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
    hen
    0.48
    oso
    0.47
    in
    0.46
    ement
    0.46
    -
    0.46
    about
    0.45
    elling
    0.45
    es
    0.44
    _
    0.44
    ul
    0.44
    POSITIVE LOGITS
     dispoz
    0.56
     качество
    0.50
    URNIZOR
    0.49
    IRCONIUM
    0.48
     cít
    0.47
     zusätz
    0.47
     gospodar
    0.46
    🈶
    0.46
     sayf
    0.46
    ស្រាយ
    0.46
    Activations Density 0.000%

    No Known Activations