© 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. 10066
    Prev
    Next
    INDEX
    Explanations

    finding actions and labels

    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
    ק
    1.31
    ა
    1.23
    rand
    1.21
    no
    1.18
    nu
    1.16
    cara
    1.16
     колле
    1.16
    nius
    1.15
    men
    1.11
    ق
    1.11
    POSITIVE LOGITS
    ння
    1.18
     Certain
    1.10
    طي
    1.10
     spleen
    1.08
     Certains
    1.06
    дання
    1.04
    ствии
    1.04
    \%,
    1.04
    тивних
    1.03
    তম
    1.03
    Activations Density 0.000%

    No Known Activations