© 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. 11463
    Prev
    Next
    INDEX
    Explanations

    function and code block separators

    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
    or
    1.13
     har
    0.92
    ↵↵
    0.91
    st
    0.89
    cal
    0.85
    by
    0.85
    ia
    0.84
    /
    0.84
     or
    0.83
    ↵
    0.83
    POSITIVE LOGITS
     FIXME
    1.49
    preliquidacion
    1.45
     Defts
    1.41
     患者
    1.32
    addPreferred
    1.31
    Methylsulfanyl
    1.31
     pavattati
    1.30
     adhipp
    1.30
    qualiter
    1.29
     gahet
    1.27
    Activations Density 0.001%

    No Known Activations