© 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. 37893
    Prev
    Next
    INDEX
    Explanations

    plan, replace, needs

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

    hypothetical AI doesn't exist yet

    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
    0.54
    ༔
    0.52
     угле
    0.51
     Христос
    0.50
    ولا
    0.50
     ше
    0.48
     importantes
    0.47
     оса
    0.46
    د
    0.46
    ות
    0.46
    POSITIVE LOGITS
    ier
    0.50
    ns
    0.48
    mun
    0.48
    മില്ല
    0.47
    ”.
    0.45
     numer
    0.45
     i
    0.44
     কিনা
    0.44
     #:
    0.43
    sted
    0.43
    Activations Density 0.000%

    No Known Activations