© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5252
    Prev
    Next
    INDEX
    Explanations

    learn courses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proporción
    0.83
    Ми
    0.78
     ги
    0.77
     Forma
    0.76
    楲
    0.74
     firmas
    0.73
     amigas
    0.72
     maine
    0.72
     solución
    0.71
     pourra
    0.71
    POSITIVE LOGITS
    ران
    0.68
     think
    0.67
    ر
    0.67
    kut
    0.63
    og
    0.63
    సై
    0.63
    סף
    0.63
    ాత్ర
    0.63
    nut
    0.63
    মহাদেশ
    0.62
    Activations Density 0.003%

    No Known Activations