© 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. 21135
    Prev
    Next
    INDEX
    Explanations

    speaking about actions and their results

    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
    etje
    -1.47
     verhind
    -1.45
     sorprendió
    -1.43
    }}</
    -1.41
    >");
    -1.38
    >
    -1.37
     eenige
    -1.35
     acht
    -1.35
     crianças
    -1.34
     disfru
    -1.34
    POSITIVE LOGITS
     this
    1.67
     also
    1.48
     knows
    1.39
     always
    1.33
     or
    1.31
     know
    1.30
     such
    1.30
     then
    1.29
     recently
    1.27
     like
    1.27
    Activations Density 0.064%

    No Known Activations