© 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. 59554
    Prev
    Next
    INDEX
    Explanations

    thrombus, ribosomal, scrupulous, Columbian

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

    abbreviated prefixes or codes that appear before terms in programming, technical, or scientific contexts.

    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
    絰
    -3.00
    
    -2.81
    i
    -2.50
    薷
    -2.48
    罈
    -2.44
    祤
    -2.42
    ⢕
    -2.41
    י
    -2.39
    沵
    -2.39
     Ahnung
    -2.38
    POSITIVE LOGITS
    饪
    2.89
    P
    2.89
    S
    2.84
    C
    2.77
    U
    2.64
    H
    2.36
     uses
    2.33
    </em>
    2.28
    B
    2.23
    赑
    2.23
    Activations Density 0.026%

    No Known Activations