© 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. 22-GEMMASCOPE-RES-131K
    7. 66963
    Prev
    Next
    INDEX
    Explanations

    many common English phrases

    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
     only
    -1.12
    やかに
    -1.02
     partículas
    -0.98
     gives
    -0.96
     devastating
    -0.96
     afectadas
    -0.96
     decided
    -0.93
     workers
    -0.93
     although
    -0.93
     established
    -0.91
    POSITIVE LOGITS
     dégust
    1.01
     délicieux
    1.01
    mbal
    0.98
     joyeux
    0.97
    おかげ
    0.96
     moeten
    0.93
     fameux
    0.92
    其妙
    0.92
    chown
    0.91
    testens
    0.91
    Activations Density 0.041%

    No Known Activations