© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8310
    Prev
    Next
    INDEX
    Explanations

    Crusades and jihad

    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
    ीकरण
    2.68
    𝜎
    2.61
    ся
    2.53
     rafters
    2.51
    보면
    2.47
    𝗻
    2.45
    manship
    2.43
    lichem
    2.39
    িং
    2.38
    iin
    2.38
    POSITIVE LOGITS
    undaria
    2.03
    ীদের
    1.96
     ну
    1.93
    &-
    1.93
    ================
    1.89
    зви
    1.89
    j
    1.89
    otry
    1.88
    ্ট
    1.86
    ကား
    1.85
    Activations Density 0.005%

    No Known Activations