© 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. 102739
    Prev
    Next
    INDEX
    Explanations

    authors and affiliations

    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
    );
    -1.74
     sudah
    -1.50
     this
    -1.49
    珖
    -1.48
     your
    -1.45
     querían
    -1.43
     podían
    -1.42
    maktadır
    -1.39
    鴣
    -1.38
    ardı
    -1.36
    POSITIVE LOGITS
    \
    1.80
     –
    1.72
    h
    1.66
    v
    1.65
    at
    1.60
    led
    1.54
    ca
    1.53
    f
    1.52
    r
    1.52
    th
    1.52
    Activations Density 0.174%

    No Known Activations