© 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. 67894
    Prev
    Next
    INDEX
    Explanations

    starts off by

    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
    <i>
    -2.33
    ↵
    -2.09
    .
    -1.85
    のですが
    -1.81
     można
    -1.78
     lorsqu
    -1.78
     "
    -1.75
     proveniente
    -1.69
    <b>
    -1.66
     "...
    -1.66
    POSITIVE LOGITS
     rigue
    2.08
     
    1.84
     inapropiados
    1.77
     proposons
    1.74
    ⎆
    1.73
    祈祷
    1.73
    媄
    1.68
     raiſ
    1.67
    ників
    1.66
    
    1.65
    Activations Density 0.003%

    No Known Activations