© 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. 21418
    Prev
    Next
    INDEX
    Explanations

    prioritizing seeking addressed delaying

    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
    matplotlib
    0.42
     james
    0.41
     Manly
    0.41
     méthodique
    0.40
    ghed
    0.40
    <unused341>
    0.38
    kontrol
    0.38
    esses
    0.38
    mongodb
    0.37
    დის
    0.37
    POSITIVE LOGITS
     agreement
    0.47
    -
    0.46
     अनुभव
    0.44
     ఇప్పటి
    0.44
     experience
    0.44
     ấy
    0.44
    ตี
    0.44
    টি
    0.43
     паро
    0.43
     которой
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.