© 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. 84527
    Prev
    Next
    INDEX
    Explanations

    quotation marks and foreign words

    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
    hålla
    -0.85
     خواهد
    -0.82
     dek
    -0.80
     semejante
    -0.79
    THOMAS
    -0.79
    ?&
    -0.78
     teater
    -0.77
     welt
    -0.77
    ysio
    -0.76
     uly
    -0.75
    POSITIVE LOGITS
    ″
    0.79
     schlägt
    0.72
     plutôt
    0.71
     снимка
    0.71
     grandes
    0.69
    Mé
    0.68
    "">
    0.68
    öng
    0.67
     benötigt
    0.66
    ்கள
    0.66
    Activations Density 0.374%

    No Known Activations