© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38164
    Prev
    Next
    INDEX
    Explanations

    young men and women

    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
     humanos
    -1.07
     регионе
    -0.93
    dì
    -0.89
    %%%%%%%%%
    -0.87
    Kids
    -0.86
    ologist
    -0.86
     alko
    -0.85
    👑
    -0.85
    therapist
    -0.85
    ErrUnexpected
    -0.84
    POSITIVE LOGITS
     intelligent
    1.14
     men
    1.02
     prominent
    0.98
     wealthy
    0.97
     learned
    0.96
     worthy
    0.96
     ladies
    0.93
     persons
    0.92
     mature
    0.90
     respectable
    0.90
    Activations Density 0.028%

    No Known Activations