© 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. 11729
    Prev
    Next
    INDEX
    Explanations

    influence permeates

    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
    دان
    1.26
    ially
    1.14
    دى
    1.13
    ﺟ
    1.09
    ,$$
    1.08
    ʍ
    1.08
    ً
    1.07
    н
    1.06
    生的
    1.06
    gae
    1.06
    POSITIVE LOGITS
     xray
    1.25
     restructure
    1.20
     optimally
    1.20
     phố
    1.20
    힝
    1.17
    ो
    1.16
    TouchableOpacity
    1.13
     évaluations
    1.10
     acrylonitrile
    1.08
    reichen
    1.07
    Activations Density 0.000%

    No Known Activations