© 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. 9702
    Prev
    Next
    INDEX
    Explanations

    clauses or phrases

    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
    ে
    2.04
    ed
    2.02
    ные
    1.75
    ة
    1.68
    ного
    1.64
    istic
    1.63
    ually
    1.57
    ▮
    1.55
    nese
    1.55
    та
    1.50
    POSITIVE LOGITS
     illetve
    1.63
    /,
    1.62
     etc
    1.62
    ع
    1.55
    <0x80>
    1.53
    ..,
    1.48
    /)
    1.47
     percolation
    1.44
     odnosno
    1.43
    it
    1.41
    Activations Density 0.001%

    No Known Activations