© 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. 7752
    Prev
    Next
    INDEX
    Explanations

    letter prepended to acronym

    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
    EdgeInsets
    -1.72
    
    -1.59
    ？！
    -1.59
    *}
    -1.47
    }
    -1.45
     useAppContext
    -1.45
    烩
    -1.40
     ‘‘
    -1.40
     IconData
    -1.40
    toDouble
    -1.39
    POSITIVE LOGITS
     of
    2.11
     each
    1.92
     your
    1.70
     mismos
    1.66
     réservés
    1.41
     anadolu
    1.38
     cóc
    1.38
    檍
    1.36
    っていました
    1.35
     podían
    1.35
    Activations Density 0.184%

    No Known Activations