© 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. 73479
    Prev
    Next
    INDEX
    Explanations

    older adults and relatives

    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
     вико
    -0.92
    núť
    -0.89
     pēc
    -0.89
    UEZ
    -0.88
     используют
    -0.88
    yenne
    -0.87
    estri
    -0.85
    ycle
    -0.85
    Socks
    -0.85
     mantienen
    -0.84
    POSITIVE LOGITS
     than
    2.50
    than
    1.69
     generation
    1.46
    Than
    1.43
     brother
    1.34
    Older
    1.30
     younger
    1.22
     generations
    1.20
     Younger
    1.20
     génération
    1.13
    Activations Density 0.017%

    No Known Activations