© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81651
    Prev
    Next
    INDEX
    Explanations

    static variable declarations

    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_34/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
    _))
    -0.85
     inan
    -0.79
     adal
    -0.78
     behar
    -0.77
    Наводи
    -0.76
    reathable
    -0.75
    蜇
    -0.73
    $_,
    -0.73
    [])
    -0.72
     blod
    -0.72
    POSITIVE LOGITS
     static
    0.83
     Self
    0.82
    izade
    0.81
     sat
    0.79
     Static
    0.77
    ̀i
    0.76
    类
    0.75
    Static
    0.74
     类
    0.73
     kullanılan
    0.72
    Activations Density 0.026%

    No Known Activations