© 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. 11253
    Prev
    Next
    INDEX
    Explanations

    establishing sets up

    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
    cstdlib
    3.23
    an
    3.02
    र
    2.91
    ר
    2.87
    𝑦
    2.78
     cili
    2.76
    cough
    2.72
     tallied
    2.67
    elapsed
    2.66
    ∈
    2.63
    POSITIVE LOGITS
    ங்கிணை
    3.04
     muestras
    2.80
    менение
    2.71
    ׁ
    2.57
    பி
    2.49
    ের
    2.47
     trat
    2.47
    健全
    2.47
     rapports
    2.42
    的操作
    2.39
    Activations Density 0.023%

    No Known Activations