© 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-262K
    7. 13273
    Prev
    Next
    INDEX
    Explanations

    http request

    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
    Bindings
    0.92
    ExternalTaskPojo
    0.86
    莜
    0.83
    াজন
    0.81
    Computed
    0.80
    Бі
    0.80
     Jara
    0.79
    QLabel
    0.78
    CollectedField
    0.78
    കല
    0.77
    POSITIVE LOGITS
     request
    0.82
    request
    0.76
     rö
    0.68
     chịu
    0.67
     lol
    0.66
    <0xB9>
    0.65
    เพื่อ
    0.65
    ifle
    0.64
    ),
    0.64
     यासाठी
    0.64
    Activations Density 0.001%

    No Known Activations