© 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. 90414
    Prev
    Next
    INDEX
    Explanations

    record player components and names

    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
    |()
    -0.74
     roll
    -0.71
    Spacer
    -0.70
     horário
    -0.68
     Intensi
    -0.68
     Barbour
    -0.68
    gridy
    -0.67
     venti
    -0.67
    chein
    -0.66
     вста
    -0.66
    POSITIVE LOGITS
     needle
    0.84
     Needle
    0.84
     Pickering
    0.82
    needle
    0.81
     cart
    0.79
    startswith
    0.78
     Cart
    0.77
    カート
    0.77
     Colton
    0.76
    automatic
    0.76
    Activations Density 0.022%

    No Known Activations