© 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. 4915
    Prev
    Next
    INDEX
    Explanations

    command line utilities

    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
     («
    0.27
     ->
    0.27
     ("
    0.26
     →
    0.26
     is
    0.25
     called
    0.25
     lesión
    0.25
    ("-
    0.25
    plexity
    0.25
     lateribus
    0.25
    POSITIVE LOGITS
    ”।
    0.29
    '")
    0.28
    irat
    0.28
    ก
    0.28
    기
    0.28
    ק
    0.27
    '",
    0.27
     Хотя
    0.27
    évrier
    0.27
    ”;
    0.26
    Activations Density 0.175%

    No Known Activations