© 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. 60240
    Prev
    Next
    INDEX
    Explanations

    technical audio and media descriptions

    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
     amplify
    -0.84
    SQUARE
    -0.84
     baden
    -0.80
     parabolic
    -0.78
     συγκ
    -0.77
    тана
    -0.77
    窣
    -0.76
     centrifugal
    -0.75
    anhas
    -0.73
     Margot
    -0.72
    POSITIVE LOGITS
     baffle
    0.92
     ané
    0.82
     psycho
    0.80
     دولار
    0.79
    闌
    0.76
     sunrise
    0.75
    ǽ
    0.74
    ubert
    0.72
     Usher
    0.72
    ầy
    0.69
    Activations Density 0.018%

    No Known Activations