© 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. 91390
    Prev
    Next
    INDEX
    Explanations

    programs instilled

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

    fully completed

    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
     ScriptInterface
    0.55
     不
    0.52
     あなた
    0.51
     Tiki
    0.50
     ครอง
    0.50
     оружи
    0.49
     UIImage
    0.49
     लिखी
    0.49
     って
    0.48
     其
    0.48
    POSITIVE LOGITS
    ран
    0.48
    rider
    0.47
    каз
    0.46
     confuses
    0.46
    раб
    0.45
    árd
    0.45
    7
    0.45
    д
    0.44
    то
    0.43
    ம்ம
    0.43
    Activations Density 0.001%

    No Known Activations