© 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. 65788
    Prev
    Next
    INDEX
    Explanations

    author information and code comments

    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
     membag
    -1.07
     Paket
    -1.05
     seite
    -1.04
     wilden
    -1.02
    länge
    -1.02
     ceket
    -1.01
     memeriksa
    -1.00
     mewujudkan
    -1.00
    CÓMO
    -0.98
     alkoh
    -0.96
    POSITIVE LOGITS
     probably
    1.16
     to
    1.16
     see
    1.09
     didn
    1.07
     doesn
    1.05
     (
    1.02
    那一
    1.01
     actually
    0.99
     will
    0.97
     gehörte
    0.96
    Activations Density 0.000%

    No Known Activations