© 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. 123687
    Prev
    Next
    INDEX
    Explanations

    software features

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "feature" in technical or programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    栊
    -2.17
    s
    -2.13
     esquina
    -2.06
    rierten
    -2.06
     tragé
    -1.99
     Menschheit
    -1.88
     Polskiego
    -1.88
    seperti
    -1.86
    ات
    -1.85
     prensa
    -1.84
    POSITIVE LOGITS
    o
    2.81
    e
    2.70
    to
    2.34
    GRAFIA
    2.27
    al
    2.27
        
    2.20
     следующих
    2.20
    re
    2.19
     devem
    2.14
     '+':
    2.14
    Activations Density 0.009%

    No Known Activations