© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12244
    Prev
    Next
    INDEX
    Explanations

    center or centered content

    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_22/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
     anything
    -1.07
    pls
    -0.97
    Життєпис
    -0.97
     abbiano
    -0.94
    keda
    -0.93
     méthodes
    -0.93
    !】
    -0.92
    ानी
    -0.92
     awakeFromNib
    -0.90
     versions
    -0.88
    POSITIVE LOGITS
    を中心に
    0.90
     државе
    0.90
    Prologue
    0.90
    ׇ
    0.89
    瘪
    0.89
    是一款
    0.86
    Симпто
    0.82
    mación
    0.81
     Not
    0.80
    Библи
    0.79
    Activations Density 0.002%

    No Known Activations