© 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. 35234
    Prev
    Next
    INDEX
    Explanations

    citations and titles

    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
     усилия
    -0.97
    cenza
    -0.95
     »,
    -0.95
    }}^{\
    -0.93
     bestaande
    -0.93
    >*/
    -0.90
     недостатки
    -0.89
    娥
    -0.88
     попы
    -0.88
    reno
    -0.88
    POSITIVE LOGITS
     by
    1.29
     discuter
    0.97
     japones
    0.92
     book
    0.92
     plomo
    0.90
     cuivre
    0.90
     where
    0.90
     fresa
    0.89
     hormigón
    0.88
     visuel
    0.88
    Activations Density 0.027%

    No Known Activations