© 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. 10757
    Prev
    Next
    INDEX
    Explanations

    human classification and roles

    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
    マウス
    1.21
    TSP
    1.19
     తిన
    1.16
     Å
    1.16
    ähr
    1.13
     dağı
    1.12
    ம
    1.12
    ાવ
    1.11
    chließlich
    1.11
     Rahmen
    1.09
    POSITIVE LOGITS
    Councillor
    1.25
    unlike
    1.20
     gentlemen
    1.17
    clause
    1.15
     gentleman
    1.10
    >′
    1.09
    Termination
    1.09
     Gentleman
    1.09
    s
    1.08
     Gentlemen
    1.07
    Activations Density 0.000%

    No Known Activations