© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60342
    Prev
    Next
    INDEX
    Explanations

    birds, plants, and conditions

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

    specialized terminology including bird names, medical conditions, and religious/philosophical concepts.

    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
    s
    -3.28
    u
    -2.59
    
    -2.53
    呖
    -2.53
    c
    -2.39
    螣
    -2.31
    螓
    -2.31
    軚
    -2.28
    
    -2.27
    ୈ
    -2.23
    POSITIVE LOGITS
    上官
    2.33
    迂
    2.23
    These
    2.20
     Our
    2.11
    逡
    2.08
     Weird
    2.02
     feverish
    1.96
    .
    1.92
    蜷
    1.91
    They
    1.90
    Activations Density 0.023%

    No Known Activations