© 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. 10425
    Prev
    Next
    INDEX
    Explanations

    section introductions

    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
    ]
    -1.97
    If
    -1.91
    ちなみに
    -1.80
    \
    -1.80
     '
    -1.78
    (
    -1.72
    The
    -1.67
    --
    -1.62
    Even
    -1.61
     When
    -1.60
    POSITIVE LOGITS
    erintah
    2.20
    馓
    1.70
     tempel
    1.70
     exploiting
    1.66
    ܙ
    1.66
    
    1.66
    آباد
    1.63
    齜
    1.63
    dly
    1.62
     alcuni
    1.61
    Activations Density 0.004%

    No Known Activations