© 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. 85088
    Prev
    Next
    INDEX
    Explanations

    Ely or Emerson followed by common suffixes

    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
    ？”
    -2.55
    鉏
    -2.53
    裢
    -2.48
    不
    -2.44
    还真是
    -2.42
    cursions
    -2.39
    ......”
    -2.30
    塍
    -2.28
    利
    -2.28
    😿
    -2.27
    POSITIVE LOGITS
    (
    2.91
    or
    2.77
    1
    2.67
    [
    2.63
    n
    2.59
    )
    2.59
    *
    2.45
    ,'
    2.38
    ]
    2.38
    7
    2.34
    Activations Density 0.006%

    No Known Activations