© 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. 11135
    Prev
    Next
    INDEX
    Explanations

    integrity, tomatoes, Rosal

    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
    t
    3.94
    ন
    3.89
    د
    3.45
    н
    3.40
    tat
    3.39
    er
    3.39
    ר
    3.25
    р
    3.22
    torn
    3.22
    n
    3.21
    POSITIVE LOGITS
     extranjeros
    3.00
    म
    2.85
    ດ້
    2.85
    ጨማሪ
    2.74
    間の
    2.71
     outperforms
    2.69
     sposób
    2.68
     apoi
    2.67
    Så
    2.66
     Così
    2.62
    Activations Density 0.100%

    No Known Activations