© 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-65K
    7. 2056
    Prev
    Next
    INDEX
    Explanations

    Gemma

    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_65k_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
     being
    0.29
    nThe
    0.29
     quantifying
    0.29
    使用
    0.29
    参数
    0.28
    ==
    0.28
     judgments
    0.28
    所得
    0.28
    将
    0.28
    存在
    0.27
    POSITIVE LOGITS
     outskirts
    0.36
     behest
    0.34
     consulate
    0.33
     forefront
    0.33
     края
    0.31
     lighthouse
    0.30
     penthouse
    0.29
     airport
    0.29
     streets
    0.29
     confines
    0.29
    Activations Density 0.239%

    No Known Activations