© 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. 7944
    Prev
    Next
    INDEX
    Explanations

    color and interface elements

    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
     "
    -2.73
    a
    -2.64
    ”
    -2.59
     *
    -2.53
    -"
    -2.50
     -
    -2.48
    </em>
    -2.48
     
    -2.45
    <em>
    -2.42
    _
    -2.36
    POSITIVE LOGITS
    because
    2.69
    ᚹ
    2.50
    屃
    2.48
    薷
    2.47
    
    2.44
     ſy
    2.36
    ﮯ
    2.30
    뀝
    2.27
    ❗️
    2.25
    嚳
    2.23
    Activations Density 0.001%

    No Known Activations