© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41634
    Prev
    Next
    INDEX
    Explanations

    links descriptor to elaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    变
    0.42
    就可以
    0.42
    施工
    0.41
     for
    0.41
    徭
    0.41
    路线
    0.41
    人员
    0.40
     jest
    0.39
     worst
    0.39
    حال
    0.39
    POSITIVE LOGITS
     клави
    0.46
     addr
    0.45
     содержа
    0.44
    センス
    0.43
     опера
    0.43
    COLOG
    0.42
     ArrayIndex
    0.42
     pinMode
    0.41
    ⛪
    0.41
     incluyen
    0.40
    Activations Density 0.003%

    No Known Activations