© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58293
    Prev
    Next
    INDEX
    Explanations

    code indentation levels

    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
    ս
    -0.75
    Sergio
    -0.71
    Voy
    -0.69
    Darren
    -0.68
    베
    -0.68
    В
    -0.66
     Đi
    -0.66
    Khi
    -0.65
    VIEW
    -0.65
    取り
    -0.65
    POSITIVE LOGITS
    favicon
    0.75
    ffffffff
    0.74
     Qian
    0.72
     dovrebbe
    0.71
    Leftrightarrow
    0.71
     STEWART
    0.70
    áska
    0.70
    具合
    0.70
    GLint
    0.69
    ONI
    0.69
    Activations Density 0.330%

    No Known Activations