© 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. 22-GEMMASCOPE-RES-131K
    7. 15042
    Prev
    Next
    INDEX
    Explanations

    manage entities and states

    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
     ayrıca
    -0.92
     Geheimnis
    -0.91
     ficando
    -0.90
    §
    -0.87
    お好み
    -0.87
     więcej
    -0.86
    شنامهٔ
    -0.86
     enquanto
    -0.86
    ׳
    -0.85
     funkcji
    -0.85
    POSITIVE LOGITS
     it
    2.11
     its
    2.03
     thereof
    1.89
     them
    1.77
     ones
    1.28
    それを
    1.24
     hacerlo
    1.23
     therein
    1.20
     melakukannya
    1.15
     및
    1.09
    Activations Density 0.123%

    No Known Activations