© 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. 53847
    Prev
    Next
    INDEX
    Explanations

    license files

    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
     universitaria
    -0.91
    </table>
    -0.88
     pié
    -0.86
     subtly
    -0.83
    🔂
    -0.82
    Fernseh
    -0.81
    り返
    -0.80
     tertentu
    -0.80
    cán
    -0.80
     enceinte
    -0.79
    POSITIVE LOGITS
     большого
    0.88
     disparities
    0.85
    wände
    0.80
     فريبيس
    0.80
    fft
    0.80
    ective
    0.78
    greja
    0.77
    ureusement
    0.76
    cols
    0.75
     речь
    0.75
    Activations Density 0.002%

    No Known Activations