© 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. 97808
    Prev
    Next
    INDEX
    Explanations

    scavenger, Ska, Scaevola

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

    words beginning with "sca" like "scavenger," "scared," and "Scaggs," with particularly high activation for proper names.

    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_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
    selin
    -0.79
    homa
    -0.71
    出す
    -0.70
    elang
    -0.69
    aternion
    -0.69
    Kontak
    -0.69
     elämä
    -0.68
     universality
    -0.68
    logits
    -0.68
    立即
    -0.68
    POSITIVE LOGITS
     sca
    1.68
     Sca
    1.37
    sca
    1.30
     ска
    1.23
    Sca
    1.22
     Ска
    1.02
     scavenger
    0.99
     SCA
    0.99
     Scar
    0.90
     scavenging
    0.86
    Activations Density 0.020%

    No Known Activations