© 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. 72675
    Prev
    Next
    INDEX
    Explanations

    specific concept introducers

    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
     لأنه
    -1.58
    /
    -1.41
     fournir
    -1.41
     verhindert
    -1.40
     diverses
    -1.39
     benutzt
    -1.38
     indiquer
    -1.37
     sientes
    -1.36
     rése
    -1.34
    jesus
    -1.34
    POSITIVE LOGITS
     and
    2.53
     It
    1.77
     also
    1.76
     which
    1.73
     of
    1.70
     There
    1.61
     también
    1.57
     For
    1.53
     at
    1.47
     Also
    1.47
    Activations Density 0.100%

    No Known Activations