© 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. 33285
    Prev
    Next
    INDEX
    Explanations

    ground truth

    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
     quits
    -0.74
    #}
    -0.73
    mphs
    -0.70
    IsOptional
    -0.69
    implementation
    -0.68
    ectors
    -0.68
    捗
    -0.67
     ५
    -0.67
     excellent
    -0.66
     Temperaturen
    -0.66
    POSITIVE LOGITS
    warte
    0.73
     DIC
    0.71
     Assays
    0.70
    コ
    0.69
    nsw
    0.68
    Recording
    0.67
    Eating
    0.67
     attachments
    0.66
     Eating
    0.65
     ГИ
    0.65
    Activations Density 0.041%

    No Known Activations