© 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. 44395
    Prev
    Next
    INDEX
    Explanations

    Topics and technical terms

    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
    ↵↵
    -2.30
     untuk
    -2.23
    )$
    -2.23
     classy
    -2.22
     ursprüng
    -2.16
    
    -2.14
     yeniden
    -2.11
    椏
    -2.11
     koruyucu
    -2.09
    蕓
    -2.09
    POSITIVE LOGITS
    .
    3.36
    </strong>
    2.64
    )
    2.25
    0
    2.20
    om
    2.14
    埽
    2.14
    菒
    2.09
    硨
    2.08
     persiste
    2.08
     подходит
    2.08
    Activations Density 0.001%

    No Known Activations