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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 1970
    Prev
    Next
    INDEX
    Explanations

    links to downloads

    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
    에
    1.32
    لى
    1.05
    ULL
    0.96
    AP
    0.93
    に
    0.93
    ah
    0.93
    ار
    0.93
    L
    0.93
    RACT
    0.89
    ULAR
    0.89
    POSITIVE LOGITS
    𝘢
    1.59
    ти
    1.37
    т
    1.37
    𝘴
    1.25
    𝘨
    1.24
    𝘮
    1.23
    te
    1.20
    groups
    1.19
    тэй
    1.17
    𝘳
    1.17
    Activations Density 0.044%

    No Known Activations