© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 576
    Prev
    Next
    INDEX
    Explanations

    solve the

    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_29_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
     забезпе
    0.72
    <unused2148>
    0.69
    Warum
    0.67
     अक्सर
    0.66
    Aunque
    0.66
     виклика
    0.65
     обеспечивает
    0.65
    <unused2171>
    0.64
     kvůli
    0.64
     λόγω
    0.64
    POSITIVE LOGITS
    </h2>
    0.82
     its
    0.78
     any
    0.77
     them
    0.77
    </h1>
    0.76
     your
    0.75
    </h3>
    0.72
     the
    0.72
     […]
    0.71
     respective
    0.71
    Activations Density 4.500%

    No Known Activations