© 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-16K
    7. 1418
    Prev
    Next
    INDEX
    Explanations

    state and quality words

    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_16k_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
    们的
    0.91
     ב
    0.89
     های
    0.89
     מ
    0.89
     את
    0.88
    での
    0.79
     ש
    0.79
     出
    0.78
     أبو
    0.78
    های
    0.77
    POSITIVE LOGITS
    <unused2151>
    0.96
    <unused484>
    0.94
     interstitiis
    0.94
    efois
    0.93
    <unused1169>
    0.92
    <unused2176>
    0.92
    เมริกา
    0.91
    лость
    0.91
    <unused1861>
    0.91
    <unused2184>
    0.90
    Activations Density 0.421%

    No Known Activations