© 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. 109812
    Prev
    Next
    INDEX
    Explanations

    vertebral segments or kV

    np_acts-logits-general · gemini-2.5-flash-lite

    numerical values and measurements in scientific or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    volt
    -0.77
     unpack
    -0.76
    V
    -0.72
     AGM
    -0.69
     Briggs
    -0.69
    v
    -0.67
    pageY
    -0.66
     popul
    -0.65
     Bryce
    -0.65
     Eureka
    -0.64
    POSITIVE LOGITS
     bays
    1.20
     hole
    0.97
    dication
    0.96
     holes
    0.88
     kV
    0.87
     spans
    0.85
     отверсти
    0.85
     span
    0.85
     bay
    0.85
    spans
    0.82
    Activations Density 0.108%

    No Known Activations