© 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. 48741
    Prev
    Next
    INDEX
    Explanations

    easy example

    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
     Diret
    0.50
     ENTRE
    0.49
    cn
    0.46
     SAN
    0.45
     B
    0.44
     Sq
    0.44
     L
    0.44
     M
    0.43
     Lions
    0.43
     Bao
    0.43
    POSITIVE LOGITS
    條件
    0.46
    тні
    0.44
    تمر
    0.43
     firepower
    0.43
     atrophy
    0.43
    تالي
    0.43
    গতির
    0.43
    ненко
    0.41
    xSpeed
    0.41
    voja
    0.41
    Activations Density 0.007%

    No Known Activations