© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6517
    Prev
    Next
    INDEX
    Explanations

    google ai urls

    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
     Online
    0.93
    .
    0.84
     Male
    0.83
     Improve
    0.82
     Web
    0.82
    ~
    0.82
     Rescue
    0.80
     Building
    0.78
     Text
    0.78
     Skilled
    0.77
    POSITIVE LOGITS
    googleapis
    1.17
    CFBundle
    1.04
    ǒu
    1.02
    LOLLIPOP
    0.98
     kojem
    0.97
    逺
    0.95
    uga
    0.94
    role
    0.93
    astra
    0.93
    asana
    0.92
    Activations Density 0.042%

    No Known Activations