© 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. 58784
    Prev
    Next
    INDEX
    Explanations

    specific list items

    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
    8
    -2.31
    7
    -2.22
    9
    -2.16
     was
    -2.11
    1
    -2.06
    6
    -2.03
    atellite
    -1.98
    5
    -1.91
    4
    -1.90
    nością
    -1.89
    POSITIVE LOGITS
     to
    1.88
    archiwizowane
    1.81
     quí
    1.79
    abortion
    1.66
     prêts
    1.63
    preferably
    1.62
    羸
    1.61
    neither
    1.54
    yeah
    1.50
    really
    1.49
    Activations Density 0.068%

    No Known Activations