© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19224
    Prev
    Next
    INDEX
    Explanations

    the [noun] or in each

    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
     if
    -1.82
    .
    -1.67
     žád
    -1.55
     «
    -1.52
     is
    -1.52
     одном
    -1.49
     [
    -1.47
    -
    -1.41
    ztes
    -1.41
     ponieważ
    -1.41
    POSITIVE LOGITS
     that
    2.00
     of
    1.83
     such
    1.56
     그것
    1.51
    굉
    1.49
     niya
    1.46
    }%
    1.45
    ówczas
    1.43
     jų
    1.42
    Such
    1.41
    Activations Density 0.225%

    No Known Activations