© 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. 133842
    Prev
    Next
    INDEX
    Explanations

    building out

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

    good for specific uses

    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
    _
    0.64
    :
    0.62
    ,
    0.58
    t
    0.54
    ;
    0.52
    🎧
    0.52
    Entertainment
    0.50
    Audio
    0.50
    ._
    0.49
    ი
    0.49
    POSITIVE LOGITS
     Saleh
    0.55
     policiais
    0.49
     fisherman
    0.48
     बेरोजगार
    0.48
    ब्राह
    0.47
     rapaz
    0.46
     policía
    0.46
    ントリー
    0.46
     когато
    0.46
     driveway
    0.45
    Activations Density 0.000%

    No Known Activations