© 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. 9-GEMMASCOPE-2-RES-16K
    7. 711
    Prev
    Next
    INDEX
    Explanations

    small businesses and rules

    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_9_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
    ía
    2.21
    에
    2.06
    难道
    2.06
    に
    1.98
    সাথে
    1.94
    ów
    1.93
    𝙎
    1.92
    ش
    1.90
     заявление
    1.86
    тат
    1.83
    POSITIVE LOGITS
    ात
    2.34
    e
    2.18
    ে
    2.11
    ことにより
    2.07
    মনি
    2.02
    tede
    1.92
    eur
    1.89
    listar
    1.87
    anego
    1.86
    eurs
    1.85
    Activations Density 0.977%

    No Known Activations