© 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. 127893
    Prev
    Next
    INDEX
    Explanations

    introduction or metadata markers

    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
     also
    -1.80
     también
    -1.76
     também
    -1.48
     Also
    -1.46
     були
    -1.38
     også
    -1.35
     також
    -1.34
     aussi
    -1.32
     jsou
    -1.31
     meinem
    -1.31
    POSITIVE LOGITS
    Uti
    1.23
     maillot
    1.20
    Merci
    1.16
     Aé
    1.16
     pirata
    1.13
     orde
    1.12
    业绩
    1.12
    gehe
    1.10
     correcte
    1.10
     roche
    1.07
    Activations Density 0.102%

    No Known Activations