© 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. 31721
    Prev
    Next
    INDEX
    Explanations

    DO NOT EDIT

    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
    stasy
    -0.77
    東日本
    -0.75
    sif
    -0.74
    opus
    -0.71
    ense
    -0.71
     важно
    -0.69
    нент
    -0.68
    pgfmath
    -0.68
     abscess
    -0.67
    ButtonGroup
    -0.67
    POSITIVE LOGITS
     NAVY
    0.76
    GROUND
    0.71
     مشتری
    0.71
     folosi
    0.69
     Winters
    0.69
     Busse
    0.68
    יסטוריה
    0.68
     regretted
    0.66
    Zim
    0.66
    Dishwasher
    0.65
    Activations Density 0.021%

    No Known Activations