© 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. 93062
    Prev
    Next
    INDEX
    Explanations

    date and time formatting

    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
     הג
    -0.86
    CheckBreak
    -0.81
     אירו
    -0.80
    -0.74
     tubular
    -0.73
    ogna
    -0.71
    婆
    -0.71
     monitor
    -0.70
     Ascot
    -0.68
     обсу
    -0.67
    POSITIVE LOGITS
     format
    0.98
    "><?=
    0.82
    CLICK
    0.81
    PATTERN
    0.80
     格式
    0.80
     FORMAT
    0.79
     cristiana
    0.78
    format
    0.77
    格式
    0.76
    Format
    0.75
    Activations Density 0.007%

    No Known Activations