© 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. 105375
    Prev
    Next
    INDEX
    Explanations

    market revolution art

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

    models compatible or similar

    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
    ंसारी
    0.49
    方は
    0.48
     townships
    0.46
    挎
    0.46
     SISO
    0.45
    രക്ഷ
    0.45
     Minimum
    0.44
    रोना
    0.44
    ንያ
    0.44
    ریہ
    0.44
    POSITIVE LOGITS
    ினர்
    0.54
    dat
    0.45
    ;";
    0.44
    strncpy
    0.44
    ಿನ
    0.43
    typen
    0.43
     p
    0.42
     মার্চ
    0.42
     সিগারে
    0.42
    expandedTitle
    0.42
    Activations Density 0.002%

    No Known Activations