© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84438
    Prev
    Next
    INDEX
    Explanations

    questions and statements

    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
     maxlength
    -1.00
    tillinger
    -0.95
    ‹
    -0.94
     fielder
    -0.94
    weeted
    -0.93
    TOOLBAR
    -0.90
    zeera
    -0.90
    barten
    -0.89
    joen
    -0.89
    verket
    -0.88
    POSITIVE LOGITS
    already
    1.19
     already
    1.15
     bereits
    1.09
     you
    1.05
     readers
    1.03
     уже
    1.03
     сейчас
    1.02
     yourselves
    1.02
     già
    1.01
    Already
    1.00
    Activations Density 0.022%

    No Known Activations