© 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. 15299
    Prev
    Next
    INDEX
    Explanations

    options

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     dacă
    -2.52
    to
    -2.48
    on
    -2.45
     we
    -2.45
     ofrecen
    -2.44
     that
    -2.42
     așa
    -2.39
     and
    -2.31
     llegan
    -2.27
     admiten
    -2.22
    POSITIVE LOGITS
    灕
    2.91
    𖡼
    2.58
    ↵↵
    2.58
     був
    2.56
    
    2.52
    </h3>
    2.45
    เกง
    2.38
    葙
    2.31
    Most
    2.28
    日曜日
    2.27
    Activations Density 0.008%

    No Known Activations