© 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. 22-GEMMASCOPE-RES-131K
    7. 65084
    Prev
    Next
    INDEX
    Explanations

    id fields and identifiers

    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_22/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
     it
    -1.27
     his
    -1.10
     not
    -1.10
     wollte
    -0.99
    ();*/
    -0.98
     no
    -0.97
     hieß
    -0.96
     that
    -0.95
    preuve
    -0.93
     M
    -0.91
    POSITIVE LOGITS
    erobic
    1.20
    他們的
    1.19
    Nieuwe
    1.10
    というわけで
    1.09
    もあって
    1.05
    шему
    1.03
     häm
    1.03
    Their
    1.02
    ounid
    1.00
    Новые
    1.00
    Activations Density 0.008%

    No Known Activations