© 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. 11962
    Prev
    Next
    INDEX
    Explanations

    software download links

    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
     we
    0.67
    -
    0.64
    /
    0.61
     abbiamo
    0.58
     সু
    0.56
     albeit
    0.55
     lleva
    0.55
     particularly
    0.54
     they
    0.54
     spor
    0.53
    POSITIVE LOGITS
    compiler
    0.64
    noodles
    0.61
    assignments
    0.61
    private
    0.60
    <unused337>
    0.57
    usage
    0.57
    installer
    0.56
    Recorder
    0.56
    ඨ
    0.55
    CURRENT
    0.54
    Activations Density 0.026%

    No Known Activations