© 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. 52959
    Prev
    Next
    INDEX
    Explanations

    am pm time stamps

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

    autoit script

    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
    untary
    0.43
    前景
    0.41
    클
    0.41
     Sellers
    0.40
     প্রান্তে
    0.40
     Buyers
    0.40
    ल्डेन
    0.40
    ോള
    0.40
     एक्ट
    0.38
    하다고
    0.38
    POSITIVE LOGITS
    <sup>
    0.48
    <em>
    0.39
    Contrast
    0.39
    Chứng
    0.36
    ┇
    0.36
    <sub>
    0.36
     الشر
    0.36
    FromArray
    0.36
    ართ
    0.36
     Contrast
    0.35
    Activations Density 0.014%

    No Known Activations