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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32136
    Prev
    Next
    INDEX
    Explanations

    headings or labels

    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
    KindOfClass
    -0.87
    stasi
    -0.87
    関わ
    -0.85
    してみると
    -0.82
    🎎
    -0.81
     withstand
    -0.81
    odacty
    -0.80
     Breaking
    -0.79
     removes
    -0.79
     memastikan
    -0.79
    POSITIVE LOGITS
     habia
    0.88
    )}+\
    0.80
     gera
    0.80
    //</
    0.79
    蠕
    0.78
    ((&
    0.77
    generation
    0.77
     presently
    0.76
    mühle
    0.76
    '<
    0.74
    Activations Density 0.000%

    No Known Activations