© 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. 38300
    Prev
    Next
    INDEX
    Explanations

    phrases and lists

    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
     objectAtIndex
    -1.07
    Rujukan
    -0.99
     ilustracji
    -0.97
    合わせた
    -0.96
    hesda
    -0.96
     pegatina
    -0.96
     envoyé
    -0.96
    탉
    -0.96
    urement
    -0.95
    eded
    -0.94
    POSITIVE LOGITS
    ACGIH
    0.92
     kuten
    0.91
     none
    0.89
     Through
    0.89
     $
    0.87
     Smith
    0.87
     усі
    0.85
    IVERS
    0.85
     miten
    0.85
     немає
    0.85
    Activations Density 0.004%

    No Known Activations