© 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. 30937
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structural elements

    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
    Only
    -0.80
    }}"
    -0.79
     Kühlschrank
    -0.77
    Berkeley
    -0.75
    carolina
    -0.75
    ambah
    -0.74
     custodi
    -0.74
     Queensland
    -0.74
     Berkeley
    -0.73
     Russians
    -0.73
    POSITIVE LOGITS
     display
    0.80
     зимой
    0.79
     Kammer
    0.77
     Otero
    0.73
    tubers
    0.69
    涨
    0.68
     absc
    0.68
     Motorcycles
    0.68
    sms
    0.68
    ’
    0.67
    Activations Density 0.003%

    No Known Activations