© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102030
    Prev
    Next
    INDEX
    Explanations

    hello everyone

    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_10/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
    s
    -1.67
    -
    -1.63
     alcune
    -1.57
     esempi
    -1.48
    其他
    -1.46
     Schülern
    -1.46
     siendo
    -1.45
    }$
    -1.44
    h
    -1.43
     THOSE
    -1.41
    POSITIVE LOGITS
    鸶
    2.20
     estekak
    2.09
     bleus
    1.95
     kablo
    1.82
     vernac
    1.80
     ados
    1.79
     findes
    1.76
     coque
    1.73
     azule
    1.70
     fofo
    1.69
    Activations Density 0.007%

    No Known Activations