© 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. 77958
    Prev
    Next
    INDEX
    Explanations

    recording or reporting results

    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
     Lester
    -0.77
     Prüfung
    -0.76
    southwest
    -0.73
    usse
    -0.71
    Arun
    -0.71
     proposition
    -0.70
     onto
    -0.68
     lin
    -0.68
    ();}
    -0.68
     ele
    -0.67
    POSITIVE LOGITS
     recorded
    1.61
     recording
    1.42
     record
    1.31
    记录
    1.30
    recorded
    1.27
    record
    1.23
     Recorded
    1.21
    Recorded
    1.20
     records
    1.17
    RECORD
    1.17
    Activations Density 0.023%

    No Known Activations