© 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. 128041
    Prev
    Next
    INDEX
    Explanations

    throw of

    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
    which
    -2.86
    During
    -2.53
     tries
    -2.50
    from
    -2.45
    From
    -2.42
    With
    -2.36
     от
    -2.34
    H
    -2.34
    Even
    -2.34
    IS
    -2.33
    POSITIVE LOGITS
     criada
    2.73
    ᥬ
    2.67
    掼
    2.41
    龗
    2.34
    昳
    2.31
    歃
    2.30
    瘣
    2.28
    hemd
    2.28
     gewi
    2.25
    “
    2.25
    Activations Density 0.006%

    No Known Activations