© 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. 66254
    Prev
    Next
    INDEX
    Explanations

    names and common English words

    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
     sudadera
    -2.30
    During
    -2.28
    Because
    -2.19
    Other
    -2.16
    While
    -2.11
    最后由
    -2.08
     aguj
    -2.05
    ‫‪
    -2.03
    𖥦
    -1.97
    Even
    -1.94
    POSITIVE LOGITS
     to
    2.97
     ‘
    2.30
     along
    1.89
     among
    1.80
     called
    1.80
     a
    1.75
     “
    1.68
    )
    1.67
    平时
    1.58
    拊
    1.58
    Activations Density 0.001%

    No Known Activations