© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8938
    Prev
    Next
    INDEX
    Explanations

    finding specific terms

    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
    一些
    -1.52
    ما
    -1.38
     sélections
    -1.36
     própri
    -1.35
    :
    -1.34
     tantôt
    -1.34
     sortant
    -1.31
    .
    -1.30
    Some
    -1.29
    有些
    -1.28
    POSITIVE LOGITS
     in
    2.34
     with
    1.80
     who
    1.69
     that
    1.60
     at
    1.54
     which
    1.53
     where
    1.53
     for
    1.51
     aparece
    1.49
     whose
    1.47
    Activations Density 0.139%

    No Known Activations