© 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. 11531
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

    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
    mapStateToProps
    -1.09
     SafeMath
    -1.08
     bär
    -1.06
    ‌.
    -1.02
     eneste
    -1.01
    курс
    -1.01
     bois
    -0.98
    ПА
    -0.97
     eind
    -0.97
     bArr
    -0.97
    POSITIVE LOGITS
     neuesten
    1.02
     erwähnten
    0.98
     ラウンド
    0.96
    PERTY
    0.93
     contex
    0.92
     чаще
    0.91
     penyanyi
    0.90
     horiz
    0.89
     eigentlichen
    0.88
    3
    0.88
    Activations Density 0.003%

    No Known Activations