© 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. 86190
    Prev
    Next
    INDEX
    Explanations

    address information

    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
     pè
    -1.75
    𐌿
    -1.73
    甗
    -1.70
    ਲ਼
    -1.70
     feu
    -1.68
     Secondo
    -1.65
    籺
    -1.63
    ᥀
    -1.60
     اولین
    -1.59
    rógeno
    -1.59
    POSITIVE LOGITS
     and
    3.22
     is
    2.55
     -
    1.91
     being
    1.90
     of
    1.90
    .”
    1.78
     made
    1.75
    }=\
    1.73
     will
    1.66
     —
    1.66
    Activations Density 0.158%

    No Known Activations