© 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. 34-GEMMASCOPE-RES-131K
    7. 83791
    Prev
    Next
    INDEX
    Explanations

    HTML markup and code snippets

    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_34/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
    nın
    -0.77
    <?=
    -0.77
    پرس
    -0.75
    perse
    -0.74
    ::~
    -0.73
     bucket
    -0.73
    ´
    -0.72
    سته
    -0.70
     пові
    -0.69
     望
    -0.69
    POSITIVE LOGITS
     Olsson
    0.90
    Skal
    0.85
    亙
    0.80
    astronomie
    0.79
     MAGAZINE
    0.78
     Russie
    0.76
    ábor
    0.75
    JOURNAL
    0.75
     getRequest
    0.73
     músculos
    0.73
    Activations Density 0.004%

    No Known Activations