© 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. 174417
    Prev
    Next
    INDEX
    Explanations

    collector where, Video shows

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

    **Max Verstappen and CRLF**

    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
    0.50
    ο
    0.48
    どころ
    0.47
    S
    0.46
     Motion
    0.46
     Dodgers
    0.46
    l
    0.46
     Lords
    0.46
    William
    0.45
    Z
    0.45
    POSITIVE LOGITS
    ány
    0.49
    اويه
    0.45
     بنا
    0.44
     nabíz
    0.44
     أع
    0.44
    ystore
    0.43
     tathapi
    0.43
     ор
    0.42
    ند
    0.42
     เฟ
    0.42
    Activations Density 0.000%

    No Known Activations