© 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. 10442
    Prev
    Next
    INDEX
    Explanations

    yeast and sapiens

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

    scientific species names, particularly those containing "sapiens" and variants of "saccharomyces".

    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
    1
    -2.41
    t
    -2.39
    芣
    -2.23
    5
    -2.20
    ází
    -2.20
    ⤹
    -2.09
    am
    -2.08
    ero
    -2.02
    9
    -1.98
    ˖
    -1.98
    POSITIVE LOGITS
    D
    2.30
    
    2.25
     leichte
    2.16
    ERS
    2.14
    V
    2.13
    P
    2.13
    L
    2.08
    瓩
    2.08
    R
    2.05
     tapping
    2.03
    Activations Density 0.006%

    No Known Activations