© 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. 72589
    Prev
    Next
    INDEX
    Explanations

    biological components and systems

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

    technical terms related to hardware, software, or biological components.

    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
     only
    -1.66
    任何人
    -1.45
     where
    -1.35
    所说
    -1.30
     ONLY
    -1.30
     December
    -1.30
     easy
    -1.25
     hanya
    -1.24
    #
    -1.20
    ж
    -1.20
    POSITIVE LOGITS
     such
    1.56
    herren
    1.24
     الأخرى
    1.20
    química
    1.16
     together
    1.16
    鴴
    1.13
     taką
    1.12
     tomates
    1.11
    stehen
    1.11
    figuren
    1.10
    Activations Density 0.252%

    No Known Activations