© 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. 10042
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers

    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
     like
    -1.50
    </code>
    -1.48
    </strong>
    -1.43
    </sub>
    -1.42
     =
    -1.40
     Arbeitnehmer
    -1.37
     verbess
    -1.34
     were
    -1.32
    "],
    -1.29
    really
    -1.28
    POSITIVE LOGITS
     Tratado
    1.53
     gitar
    1.42
     Código
    1.41
    鹀
    1.40
     levure
    1.34
    
    1.31
    𖡼
    1.30
    褡
    1.30
     karier
    1.30
     Portail
    1.30
    Activations Density 0.042%

    No Known Activations