© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 650
    Prev
    Next
    INDEX
    Explanations

    our [followed by noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ꮘ
    -2.75
     แต่
    -2.53
     thuy
    -2.48
     não
    -2.44
    鲞
    -2.39
    东西
    -2.34
     используется
    -2.34
    archiwizowane
    -2.34
    饪
    -2.33
     greateſt
    -2.30
    POSITIVE LOGITS
    self
    3.73
    h
    3.72
    c
    3.28
    r
    3.08
    t
    2.94
    as
    2.88
    o
    2.88
    f
    2.83
    k
    2.81
    u
    2.77
    Activations Density 0.070%

    No Known Activations