© 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. 22-GEMMASCOPE-RES-131K
    7. 34245
    Prev
    Next
    INDEX
    Explanations

    common english phrases

    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_22/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
    헷
    -1.12
    eaza
    -0.90
     recib
    -0.89
     vrienden
    -0.89
     vijf
    -0.86
    ときは
    -0.86
     oito
    -0.86
     têm
    -0.86
     tausend
    -0.86
     divulgação
    -0.85
    POSITIVE LOGITS
     rám
    1.01
     because
    1.01
    姓名
    0.92
     kabát
    0.89
     something
    0.88
    因为
    0.86
     completely
    0.84
     luxus
    0.83
    mathrm
    0.82
    س
    0.82
    Activations Density 0.072%

    No Known Activations