© 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. 10-GEMMASCOPE-RES-131K
    4. 71948
    Prev
    Next
    INDEX
    Explanations

    numerical percentages followed by context

    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
    without
    -1.37
    cte
    -1.36
    operating
    -1.35
     WITHOUT
    -1.34
    
    -1.32
     ilustração
    -1.30
     ferramenta
    -1.28
    莛
    -1.28
     enchufe
    -1.27
     be
    -1.25
    POSITIVE LOGITS
     of
    1.63
     this
    1.47
     for
    1.34
     if
    1.30
     概要
    1.28
     These
    1.26
     would
    1.24
    dibujos
    1.21
     also
    1.20
    сели
    1.20
    Activations Density 0.047%

    No Known Activations