© 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. 10728
    Prev
    Next
    INDEX
    Explanations

    brain and its components

    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
    क
    2.48
     refuge
    2.25
    ри
    2.25
    с
    2.24
    𝑺
    2.21
    doğan
    2.20
    ুদ
    2.20
    ित
    2.18
    ْب
    2.17
    는
    2.16
    POSITIVE LOGITS
    y
    3.72
    ে
    3.20
    m
    3.10
    ر
    3.07
    ي
    3.04
    o
    3.01
    en
    2.98
    ం
    2.98
    م
    2.94
    י
    2.85
    Activations Density 0.149%

    No Known Activations