© 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. 90448
    Prev
    Next
    INDEX
    Explanations

    source code license

    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
    かした
    -0.85
    paravant
    -0.85
    circledR
    -0.85
     particulières
    -0.81
     tenues
    -0.80
     ZEALAND
    -0.79
     elke
    -0.79
    Ö
    -0.76
     officielles
    -0.76
     mei
    -0.76
    POSITIVE LOGITS
    اير
    0.89
    istungen
    0.86
     lugs
    0.85
     near
    0.80
     cinematography
    0.79
    pontos
    0.76
     comparable
    0.75
     precipitates
    0.75
     neighborhoods
    0.73
    鄒
    0.73
    Activations Density 0.001%

    No Known Activations