© 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. 701
    Prev
    Next
    INDEX
    Explanations

    BreadCrumb and root

    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
     Ши
    0.46
    鄴
    0.46
    for
    0.44
    瓯
    0.44
    То
    0.43
     belirli
    0.43
    膘
    0.42
    നാ
    0.42
     mariage
    0.41
    this
    0.40
    POSITIVE LOGITS
     pregnancies
    0.50
     dynamite
    0.48
     natthi
    0.48
     sullen
    0.48
     dyed
    0.46
     candied
    0.46
     fermented
    0.46
    i
    0.46
     thawed
    0.45
     sprouts
    0.45
    Activations Density 0.000%

    No Known Activations