© 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. 22-GEMMASCOPE-RES-131K
    7. 67849
    Prev
    Next
    INDEX
    Explanations

    hypocretin, eye, disease, endotoxin, killer

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

    medical and scientific terms in parenthetical explanations or alternative 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_22/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
     called
    -1.24
     dubbed
    -1.13
    我也
    -1.10
     chamado
    -1.09
    øver
    -1.05
     nazy
    -1.02
    Called
    -1.00
     chamada
    -1.00
     Called
    -0.99
    called
    -0.98
    POSITIVE LOGITS
     for
    0.91
     as
    0.91
    sivu
    0.90
    してみると
    0.90
     is
    0.88
    があります
    0.87
    旋律
    0.82
    ksesta
    0.80
    ія
    0.80
     rave
    0.79
    Activations Density 0.123%

    No Known Activations