© 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. 72232
    Prev
    Next
    INDEX
    Explanations

    numbers and scales

    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
     will
    -0.79
    ┿
    -0.76
     incumb
    -0.74
     tries
    -0.74
    鲶
    -0.72
     other
    -0.71
    囔
    -0.71
     Änderungen
    -0.71
    ospital
    -0.70
     Overs
    -0.70
    POSITIVE LOGITS
     basic
    0.96
     mild
    0.92
     минима
    0.87
     superficial
    0.86
     junior
    0.86
     low
    0.85
    BaseModel
    0.85
     moderate
    0.84
    Mild
    0.84
     shortest
    0.82
    Activations Density 0.106%

    No Known Activations