© 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. 182634
    Prev
    Next
    INDEX
    Explanations

    about right

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

    nice to meet you

    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
     sabem
    0.55
    Ⲕ
    0.52
    ATEST
    0.52
     プラ
    0.50
     sapere
    0.49
    اردوش
    0.47
     terminates
    0.47
     הולנד
    0.46
     glutamate
    0.46
     tomates
    0.46
    POSITIVE LOGITS
    <0x80>
    0.56
    in
    0.52
     college
    0.48
    er
    0.48
    gutter
    0.48
     brace
    0.46
     rugby
    0.46
     maroon
    0.44
    <b>
    0.43
    strap
    0.42
    Activations Density 0.001%

    No Known Activations