© 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-16K
    7. 1214
    Prev
    Next
    INDEX
    Explanations

    end of sentences

    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_16k_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
    s
    1.56
    e
    1.38
    a
    1.29
    h
    1.13
    ați
    1.11
    economic
    1.10
    o
    1.04
    es
    1.03
    ../../
    1.03
    AC
    1.01
    POSITIVE LOGITS
    м
    1.72
    م
    1.55
    ные
    1.49
    म
    1.44
    প
    1.23
    <0xAB>
    1.20
    ம்
    1.20
    𝚝
    1.16
    ীদার
    1.13
    ку
    1.11
    Activations Density 0.750%

    No Known Activations