© 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. 34-GEMMASCOPE-RES-131K
    7. 893
    Prev
    Next
    INDEX
    Explanations

    Jeff and surnames

    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_34/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
    поль
    -0.96
     mă
    -0.81
    нија
    -0.78
     bie
    -0.77
    tened
    -0.77
     lat
    -0.76
    cw
    -0.75
     ifs
    -0.74
     champ
    -0.74
     %,
    -0.74
    POSITIVE LOGITS
    erey
    1.34
    ery
    1.22
    reys
    1.19
    ry
    1.13
     Bezos
    1.09
    ERSON
    1.08
    jeff
    0.98
    ERY
    0.97
    Jeff
    0.95
     Jeff
    0.95
    Activations Density 0.012%

    No Known Activations