© 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. 58650
    Prev
    Next
    INDEX
    Explanations

    participating in activities

    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
     exceptionally
    -2.94
    奩
    -2.89
     predominantly
    -2.81
    媗
    -2.70
     delightfully
    -2.64
     amazingly
    -2.63
     interessante
    -2.59
     delightful
    -2.59
     strikingly
    -2.58
     remarkably
    -2.56
    POSITIVE LOGITS
     There
    4.13
    There
    3.47
    When
    3.19
    During
    2.94
     When
    2.94
     If
    2.91
     Even
    2.89
    While
    2.88
    s
    2.83
     These
    2.80
    Activations Density 0.008%

    No Known Activations