© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74187
    Prev
    Next
    INDEX
    Explanations

    marble and its uses

    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
    {
    -2.59
    as
    -2.50
    ’
    -2.48
    鼉
    -2.39
    ING
    -2.38
    in
    -2.25
    花板
    -2.22
     But
    -2.20
    \
    -2.17
     If
    -2.09
    POSITIVE LOGITS
    橚
    3.03
    𓍊
    2.58
    臜
    2.55
    旄
    2.53
    蒌
    2.45
    𓋼
    2.44
    炱
    2.41
     various
    2.41
    dáms
    2.36
    镚
    2.33
    Activations Density 0.001%

    No Known Activations