© 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. 112445
    Prev
    Next
    INDEX
    Explanations

    specific technical domains

    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
     autres
    -1.35
     innych
    -1.27
     دیگر
    -1.17
     lainnya
    -1.16
     OTHER
    -1.15
     otras
    -1.10
    ります
    -1.10
     others
    -1.07
    其他
    -1.06
     člen
    -1.06
    POSITIVE LOGITS
     frequently
    1.05
     also
    1.02
     Vgl
    0.99
     these
    0.96
    \%,
    0.94
     always
    0.94
    ”،
    0.94
     constantly
    0.91
     lutego
    0.91
     синий
    0.90
    Activations Density 0.432%

    No Known Activations