© 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. 44894
    Prev
    Next
    INDEX
    Explanations

    API endpoint

    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
     isomorphisms
    1.25
    ﺩ
    1.23
     florals
    1.19
     affidavits
    1.17
    ่
    1.13
     Veja
    1.12
     positrons
    1.09
    ৯০
    1.08
    ের
    1.07
    Creo
    1.07
    POSITIVE LOGITS
    ian
    1.35
    ли
    1.30
    ib
    1.20
    st
    1.19
    ो
    1.19
    я
    1.19
    و
    1.17
    ış
    1.16
    iz
    1.16
    ная
    1.14
    Activations Density 0.000%

    No Known Activations