© 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-65K
    7. 8347
    Prev
    Next
    INDEX
    Explanations

    systems

    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_65k_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
    te
    1.04
    to
    1.04
    로
    1.00
    ர்
    0.99
    中
    0.97
    و
    0.95
    ramid
    0.95
    ა
    0.95
    is
    0.95
    তে
    0.94
    POSITIVE LOGITS
     manned
    1.02
    एस
    1.02
     урав
    0.94
     entrer
    0.94
     ठो
    0.93
    exploitation
    0.93
     ordnance
    0.92
    בוה
    0.92
    咿
    0.91
     nacionais
    0.90
    Activations Density 0.042%

    No Known Activations