© 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. 9-GEMMASCOPE-2-RES-262K
    7. 10689
    Prev
    Next
    INDEX
    Explanations

    model response

    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_9_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
    UAGES
    0.89
    writelines
    0.84
     Subsect
    0.82
    hazardous
    0.82
    ){//
    0.79
    zoic
    0.79
    각형
    0.79
     correspond
    0.79
    ]")
    0.78
    ذج
    0.78
    POSITIVE LOGITS
    د
    0.80
     ২৯
    0.76
    togel
    0.76
    イタリア
    0.74
    0.73
    й
    0.73
    ↵↵
    0.72
    rück
    0.72
    پاکستان
    0.72
    ২৮
    0.72
    Activations Density 0.319%

    No Known Activations