© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 886
    Prev
    Next
    INDEX
    Explanations

    door or doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ities
    1.68
    ↵
    1.65
    isations
    1.63
    s
    1.39
    נ
    1.31
    ب
    1.30
    sand
    1.24
    itation
    1.23
    酎
    1.23
     isomorphisms
    1.19
    POSITIVE LOGITS
    ⵚ
    1.68
    னித
    1.63
    ல்
    1.61
    лган
    1.60
    ⵅ
    1.56
    ند
    1.55
    larda
    1.54
     spô
    1.52
     врача
    1.52
    و
    1.50
    Activations Density 0.013%

    No Known Activations