© 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. 38820
    Prev
    Next
    INDEX
    Explanations

    Objective-C method starts

    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
    3
    -3.16
    6
    -2.88
    2
    -2.88
    1
    -2.73
    7
    -2.67
    5
    -2.61
    4
    -2.58
    9
    -2.50
    \
    -2.30
    $
    -2.30
    POSITIVE LOGITS
    ?”
    1.95
     _________
    1.94
     complementos
    1.93
    埽
    1.88
     considerados
    1.86
     nacidos
    1.84
    坶
    1.84
    AILY
    1.83
     quintessential
    1.80
     motivadoras
    1.80
    Activations Density 0.038%

    No Known Activations