© 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. 7556
    Prev
    Next
    INDEX
    Explanations

    special tags

    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
     When
    -1.68
     help
    -1.67
     only
    -1.60
    庭園
    -1.58
     as
    -1.55
     always
    -1.52
    縷
    -1.51
     even
    -1.47
     their
    -1.46
     helped
    -1.46
    POSITIVE LOGITS
    ’
    1.86
    THERE
    1.85
    ↵
    1.83
    which
    1.73
    yeah
    1.71
    訁
    1.67
     你
    1.64
    鸶
    1.63
    戋
    1.63
    媗
    1.61
    Activations Density 0.023%

    No Known Activations