© 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. 156177
    Prev
    Next
    INDEX
    Explanations

    without having

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

    conditional specifications and details

    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
    τ
    0.46
    debate
    0.46
    ሾ
    0.46
     temptation
    0.46
    نی
    0.44
    attacking
    0.44
     debate
    0.44
    n
    0.44
    п
    0.43
    ٤
    0.43
    POSITIVE LOGITS
     Duy
    0.52
     Buckley
    0.46
     Perpetual
    0.46
     Kunden
    0.46
    ulman
    0.45
     potrzeby
    0.43
     uitgen
    0.43
     mahal
    0.43
     предприятий
    0.42
     Packer
    0.42
    Activations Density 0.002%

    No Known Activations