© 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. 4545
    Prev
    Next
    INDEX
    Explanations

    the trevor project

    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
    '
    0.64
    ة
    0.61
    קת
    0.60
    AMP
    0.60
    ের
    0.59
    VI
    0.59
    ्ठा
    0.58
    ske
    0.57
    AMI
    0.57
    ANI
    0.57
    POSITIVE LOGITS
     stockbild
    0.90
    querysearch
    0.82
    <unused466>
    0.80
    <unused1697>
    0.80
    <unused1910>
    0.79
    <unused755>
    0.78
    <unused1672>
    0.77
    Gosudarstvennyj
    0.76
     lacer
    0.76
    ♐
    0.75
    Activations Density 0.058%

    No Known Activations