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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118928
    Prev
    Next
    INDEX
    Explanations

    legal citations and code

    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
    räger
    -0.79
    編輯
    -0.69
     clean
    -0.68
    comics
    -0.67
    clean
    -0.65
     jawaban
    -0.64
    زی
    -0.62
     interno
    -0.62
    Nép
    -0.62
    isers
    -0.61
    POSITIVE LOGITS
    笨
    0.75
    FOOTNOTES
    0.72
     Buda
    0.70
    MatInputModule
    0.69
    כז
    0.67
     utterance
    0.66
    strahlung
    0.66
    GOVERNMENT
    0.66
    ALUM
    0.66
     Prix
    0.66
    Activations Density 0.054%

    No Known Activations