© 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. 17551
    Prev
    Next
    INDEX
    Explanations

    cursor movement or location

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

    user interface elements and filters

    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
    :
    0.43
     ingenu
    0.42
    좀
    0.42
    ல்
    0.40
    숭
    0.40
    นี้
    0.39
     זה
    0.39
     вигляді
    0.39
     contributory
    0.38
    Clicked
    0.38
    POSITIVE LOGITS
    apeake
    0.42
     apabila
    0.40
     menyaksikan
    0.39
     ظِلِّ
    0.39
    ठमाड
    0.39
     Okinawa
    0.38
     பருவ
    0.38
    <0x92>
    0.38
     মাঝামা
    0.38
    りと
    0.37
    Activations Density 0.000%

    No Known Activations