© 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. 5758
    Prev
    Next
    INDEX
    Explanations

    bolding and lists followed by "this"

    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
    也是
    0.50
    حه
    0.49
    ==
    0.47
    เซีย
    0.44
     signifikan
    0.42
    虍
    0.42
    幵
    0.42
    🤧
    0.41
    㧕
    0.41
     ಕೂಡ
    0.41
    POSITIVE LOGITS
    il
    0.52
    ug
    0.48
    ógico
    0.47
    ↵
    0.46
     T
    0.46
    ils
    0.45
    us
    0.45
    ing
    0.45
    ological
    0.45
    ists
    0.44
    Activations Density 0.324%

    No Known Activations