© 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. 10-GEMMASCOPE-RES-131K
    7. 104857
    Prev
    Next
    INDEX
    Explanations

    together or combined

    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_10/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
     et
    -2.78
    -2.75
     enorme
    -2.66
    N
    -2.59
     avec
    -2.53
     két
    -2.50
     WILSON
    -2.50
    S
    -2.50
    }$
    -2.48
    冧
    -2.44
    POSITIVE LOGITS
     Also
    3.41
     Relatively
    2.84
     Numerous
    2.77
     Additionally
    2.66
     Possibly
    2.64
     Somewhat
    2.64
     However
    2.63
     Hinsicht
    2.63
     Roughly
    2.56
    棪
    2.55
    Activations Density 0.013%

    No Known Activations