© 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-262K
    7. 10096
    Prev
    Next
    INDEX
    Explanations

    starch and processing

    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
    ে
    3.25
    ଞ
    2.49
    en
    2.45
    ení
    2.38
    çalves
    2.35
    います
    2.34
    enste
    2.31
     akh
    2.28
     differentiable
    2.28
     alti
    2.24
    POSITIVE LOGITS
    ament
    2.25
    м
    2.03
    о
    1.92
    ES
    1.89
    usi
    1.87
    ون
    1.83
    inos
    1.82
    elsen
    1.76
    ring
    1.74
    ל
    1.73
    Activations Density 0.007%

    No Known Activations