Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110192
    Prev
    Next
    INDEX
    Explanations

    percentages and decimal points

    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
     Tsuk
    -0.76
    จัก
    -0.75
    zal
    -0.75
     XVIII
    -0.72
    Jg
    -0.71
    tised
    -0.70
    ダル
    -0.69
     subsidized
    -0.69
     尼
    -0.68
     wizard
    -0.67
    POSITIVE LOGITS
    fifty
    1.09
     fifty
    1.05
    Fifty
    0.97
    5
    0.96
     half
    0.87
    ½
    0.84
    Mitte
    0.83
    half
    0.82
     Fifty
    0.82
     cincuenta
    0.79
    Activations Density 0.034%

    No Known Activations