© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129928
    Prev
    Next
    INDEX
    Explanations

    committed to

    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
     schönes
    -1.73
     new
    -1.55
     umiejęt
    -1.52
     sorpresas
    -1.52
    もある
    -1.52
     novios
    -1.52
     some
    -1.51
    特有
    -1.49
     lecciones
    -1.49
     samego
    -1.49
    POSITIVE LOGITS
     maro
    1.81
     itali
    1.72
    紲
    1.68
     皇族
    1.66
     confr
    1.62
     luxem
    1.61
    </b>
    1.60
     bril
    1.59
     profe
    1.56
     prostitu
    1.55
    Activations Density 0.015%

    No Known Activations