© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71587
    Prev
    Next
    INDEX
    Explanations

    family terms and medical conditions

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates for terms related to family relations, especially grandparents and generations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     ampliar
    -2.58
     tornou
    -2.58
     cumplido
    -2.47
     начали
    -2.36
     OGSÅ
    -2.31
     fremden
    -2.30
     beträ
    -2.28
     determinadas
    -2.27
     crouched
    -2.27
     tendría
    -2.25
    POSITIVE LOGITS
    U
    3.91
    T
    3.53
    r
    3.50
    H
    3.30
    B
    3.11
    0
    3.03
    d
    3.00
    si
    2.97
    D
    2.95
    on
    2.75
    Activations Density 0.014%

    No Known Activations