© 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. 11539
    Prev
    Next
    INDEX
    Explanations

    tagging word pairs

    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
    ⤒
    1.25
     tard
    1.23
    ํานวน
    1.19
    RIM
    1.19
    oarece
    1.16
    $('#
    1.13
    îne
    1.13
    aviti
    1.12
    ṇa
    1.11
     polytope
    1.10
    POSITIVE LOGITS
    en
    1.67
    علي
    1.21
    ش
    1.21
     aphids
    1.18
    र
    1.17
    ض
    1.17
     hist
    1.16
     misrepresented
    1.14
    ﾝ
    1.12
     maintains
    1.10
    Activations Density 0.000%

    No Known Activations