© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118909
    Prev
    Next
    INDEX
    Explanations

    semiconductor compounds and devices

    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
     copying
    -0.72
    shadows
    -0.71
    ուն
    -0.71
    無駄
    -0.71
    痨
    -0.70
    书法
    -0.69
     informado
    -0.67
    といふ
    -0.66
    liday
    -0.66
    łby
    -0.66
    POSITIVE LOGITS
     Ga
    1.79
    Ga
    1.57
    Compound
    0.89
     sapphire
    0.89
    Sapphire
    0.87
     LED
    0.86
    compound
    0.84
    ZnO
    0.84
     III
    0.82
     Compound
    0.82
    Activations Density 0.112%

    No Known Activations