© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7344
    Prev
    Next
    INDEX
    Explanations

    programming keywords and actions

    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
     of
    -2.27
     and
    -2.20
     with
    -1.84
     to
    -1.49
     its
    -1.38
    ate
    -1.33
    🙁
    -1.29
     are
    -1.27
     –
    -1.27
    r
    -1.24
    POSITIVE LOGITS
    {
    1.50
     hacemos
    1.41
    ਗ਼
    1.39
     necesitamos
    1.36
    ühner
    1.35
    ätigung
    1.35
     nhưng
    1.33
     tailles
    1.33
    zember
    1.32
     PUSTAKA
    1.30
    Activations Density 0.073%

    No Known Activations