© 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. 41186
    Prev
    Next
    INDEX
    Explanations

    related to LaTeX document class

    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
    -
    -1.96
     gets
    -1.89
     believes
    -1.73
     will
    -1.73
     just
    -1.67
     went
    -1.65
     chose
    -1.65
     becomes
    -1.61
    我们将
    -1.61
    GRAFIA
    -1.59
    POSITIVE LOGITS
    嫆
    2.06
     harten
    1.87
    ⢪
    1.82
     warmen
    1.73
    ឵
    1.73
    豋
    1.71
    塒
    1.69
    artige
    1.69
    artigen
    1.68
    зраст
    1.66
    Activations Density 0.001%

    No Known Activations