© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 11076
    Prev
    Next
    INDEX
    Explanations

    configuration values like true, false, none

    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
    裵
    0.45
    衾
    0.43
     Militar
    0.41
    І
    0.39
     მთავ
    0.39
    క్
    0.38
    hna
    0.38
     시험
    0.37
     sobering
    0.37
    瑄
    0.37
    POSITIVE LOGITS
    reshold
    0.49
    automatic
    0.45
    允许
    0.45
    infini
    0.45
     allow
    0.44
    threshold
    0.44
     conservatively
    0.44
     tolerate
    0.44
    none
    0.43
     minimum
    0.42
    Activations Density 0.070%

    No Known Activations