© 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. 183451
    Prev
    Next
    INDEX
    Explanations

    progressive screening methodologies

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

    developer asking for code

    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
    <unused83>
    0.53
     लॉर्ड
    0.50
    امه
    0.50
    <unused94>
    0.50
     亀
    0.49
    <unused18>
    0.49
    ﺮ
    0.49
     quân
    0.49
    roits
    0.48
    <unused10>
    0.47
    POSITIVE LOGITS
    :
    0.54
    You
    0.52
    you
    0.49
     I
    0.47
    <em>
    0.46
     YOU
    0.45
    I
    0.45
    <code>
    0.45
     THERE
    0.44
    Yeah
    0.44
    Activations Density 0.000%

    No Known Activations