© 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. 41605
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

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

    how not what

    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
    ┣
    0.52
    ೇವಿನ
    0.51
     ዓይነ
    0.48
     стек
    0.45
     matplotlib
    0.44
    FormBorderStyle
    0.44
    圈
    0.44
     ইনডাক
    0.44
    钵
    0.44
    Tomato
    0.43
    POSITIVE LOGITS
    am
    0.57
    don
    0.48
     deva
    0.47
    werking
    0.46
    idn
    0.45
    ara
    0.45
     bruta
    0.45
     <
    0.45
    ían
    0.45
     TAT
    0.44
    Activations Density 0.000%

    No Known Activations