© 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. 687
    Prev
    Next
    INDEX
    Explanations

    mouse events: down, up, pressed

    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
    u
    -1.93
    H
    -1.92
    x
    -1.91
    L
    -1.91
    begin
    -1.86
    J
    -1.83
    T
    -1.83
    ta
    -1.79
    S
    -1.78
    E
    -1.77
    POSITIVE LOGITS
     größe
    1.63
     musia
    1.58
    楳
    1.54
     nothwendig
    1.53
    embley
    1.53
     kontaktu
    1.52
    politician
    1.51
    sailor
    1.48
     seclusion
    1.48
    đầm
    1.46
    Activations Density 0.009%

    No Known Activations