© 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-262K
    7. 10962
    Prev
    Next
    INDEX
    Explanations

    dates and versions

    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_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
    ण्यासाठी
    2.01
    ів
    1.87
    bladder
    1.86
    sulf
    1.85
    etime
    1.80
    ওয়
    1.79
    ANCIS
    1.76
    髦
    1.76
    ディスク
    1.74
    ObjectType
    1.73
    POSITIVE LOGITS
    なります
    1.84
    ுள்ளனர்
    1.74
    ận
    1.61
    er
    1.55
    unset
    1.53
    jenigen
    1.53
     günü
    1.51
    দের
    1.48
    ść
    1.47
    这一点
    1.47
    Activations Density 0.031%

    No Known Activations