© 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. 69750
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
    睒
    -3.14
    hilterra
    -2.72
    讴
    -2.70
    
    -2.66
     protestas
    -2.66
     determinados
    -2.66
     odstran
    -2.63
    磧
    -2.58
     próximas
    -2.58
     alcune
    -2.58
    POSITIVE LOGITS
    .
    4.47
    %
    2.94
    s
    2.89
    d
    2.84
    ,
    2.80
    ]
    2.66
    e
    2.64
    <
    2.63
    has
    2.41
    k
    2.38
    Activations Density 0.013%

    No Known Activations