© 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. 8316
    Prev
    Next
    INDEX
    Explanations

    verbs describing outcomes or state changes

    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
     jego
    -1.15
     åren
    -1.14
     zweif
    -1.14
     tivi
    -1.13
     befes
    -1.13
    itized
    -1.13
    arities
    -1.12
    🔍
    -1.11
    喳
    -1.11
     renfer
    -1.10
    POSITIVE LOGITS
     in
    1.55
     because
    1.36
    újo
    1.29
     også
    1.27
     however
    1.27
    目前的
    1.23
     controllare
    1.23
     However
    1.18
    karena
    1.16
     also
    1.13
    Activations Density 0.105%

    No Known Activations