© 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. 15802
    Prev
    Next
    INDEX
    Explanations

    Mr and Dr followed by names

    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
    これは
    -0.91
     WHICH
    -0.91
     которое
    -0.88
    がありますが
    -0.87
     tunik
    -0.85
     gastronomía
    -0.84
     cenas
    -0.83
     которые
    -0.83
    さすが
    -0.82
    parfum
    -0.81
    POSITIVE LOGITS
     aanbied
    1.03
     miró
    0.97
    Many
    0.91
     deleteById
    0.89
     Many
    0.89
     indian
    0.88
     Today
    0.88
    彎
    0.86
    мне
    0.85
    ampiyon
    0.85
    Activations Density 0.037%

    No Known Activations