© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1559
    Prev
    Next
    INDEX
    Explanations

    programming modules

    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
    ра
    3.27
    িল
    2.74
     streng
    2.65
    ли
    2.58
    etl
    2.45
    νες
    2.44
    ो
    2.43
    क
    2.43
    ר
    2.41
    ть
    2.41
    POSITIVE LOGITS
    se
    3.11
    sa
    2.70
    AIS
    2.64
    多い
    2.54
     aparent
    2.48
    iverso
    2.45
    pun
    2.42
    ्ञ
    2.40
    sh
    2.39
    હેર
    2.37
    Activations Density 0.347%

    No Known Activations