© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 785
    Prev
    Next
    INDEX
    Explanations

    z-index or index

    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
    ्स
    1.52
    ти
    1.40
    ্মান
    1.35
     Landmarks
    1.34
    ста
    1.30
    𝒉
    1.30
     CEST
    1.27
    س
    1.27
    등학교
    1.24
    тные
    1.23
    POSITIVE LOGITS
    গতকাল
    1.35
     impatiently
    1.25
    u
    1.24
    rangian
    1.23
    yne
    1.16
    uet
    1.15
    pcs
    1.13
     patiently
    1.11
    ol
    1.09
     immensely
    1.09
    Activations Density 0.002%

    No Known Activations