© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 64994
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

    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_22/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
     Pues
    -1.27
     Nedir
    -1.16
    噌
    -1.13
     besonderes
    -1.10
     Bisa
    -1.10
     Privacidad
    -1.09
     INGREDIENTS
    -1.09
     Особенно
    -1.08
     вопло
    -1.07
    馔
    -1.07
    POSITIVE LOGITS
    <eos>
    2.05
     in
    1.34
     it
    1.29
     and
    1.23
    انتهای
    1.15
    GRAFÍA
    1.11
    visionnement
    1.09
     peduli
    1.07
     lastly
    1.05
     before
    1.03
    Activations Density 0.002%

    No Known Activations