© 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. 73673
    Prev
    Next
    INDEX
    Explanations

    partial class declaration

    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
    ياه
    -1.81
    pueblo
    -1.78
     numerosas
    -1.78
    issory
    -1.62
     wurden
    -1.61
     cargas
    -1.57
     princí
    -1.55
     mnoho
    -1.51
    身边的
    -1.51
     abundante
    -1.47
    POSITIVE LOGITS
    6
    2.30
    4
    2.28
    5
    2.25
    2
    2.23
    3
    2.09
    9
    2.02
    7
    1.95
    酲
    1.95
    0
    1.85
    8
    1.77
    Activations Density 0.002%

    No Known Activations