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. 8701
    Prev
    Next
    INDEX
    Explanations

    date, license, version numbers

    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
    6
    -1.76
     six
    -1.45
     sixth
    -1.23
     Sixth
    -1.10
    ۶
    -1.09
     sixty
    -1.05
     Six
    -1.05
    ೬
    -1.04
    ၆
    -0.95
     Sixty
    -0.90
    POSITIVE LOGITS
    8
    0.98
    푸
    0.81
     VIII
    0.81
    yticks
    0.80
    parseFloat
    0.79
     tambi
    0.75
    =\""
    0.72
    FileInputStream
    0.71
     Illumin
    0.68
    хин
    0.68
    Activations Density 2.166%

    No Known Activations