© 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. 22-GEMMASCOPE-RES-131K
    7. 72924
    Prev
    Next
    INDEX
    Explanations

    scientific reporting and findings

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

    academic or scientific text, particularly in research papers where methodologies and findings are being presented.

    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
     vientre
    -1.49
    栝
    -1.33
     cinturón
    -1.33
    іе
    -1.31
     conseguiu
    -1.30
    hésite
    -1.30
    諡
    -1.27
     vänner
    -1.26
    コンサート
    -1.26
     different
    -1.26
    POSITIVE LOGITS
     Rektor
    1.24
     Ukraina
    1.22
     $
    1.21
    $
    1.21
    Batis
    1.18
     Nauka
    1.18
    miljø
    1.16
     אלה
    1.16
    手中
    1.16
    szön
    1.13
    Activations Density 0.467%

    No Known Activations