© 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. 118704
    Prev
    Next
    INDEX
    Explanations

    beginning phrases

    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
    haps
    -0.90
    ᱹ
    -0.90
    ًا
    -0.86
     dá
    -0.85
    :(
    -0.81
    Courses
    -0.81
     hic
    -0.80
    entown
    -0.80
     katastro
    -0.78
     jeopardize
    -0.78
    POSITIVE LOGITS
     via
    0.96
    最新章节
    0.89
     bazı
    0.86
    了很多
    0.86
    しており
    0.84
     besitzen
    0.84
    zug
    0.83
    msn
    0.82
    色々な
    0.82
    TRANSM
    0.81
    Activations Density 0.000%

    No Known Activations