© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70278
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    computer programming and technical content related to hardware interfaces and input devices.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is triggered by sequences of digits or numeric literals (especially in code or diff metadata).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Remembrance
    -0.70
     hours
    -0.69
     Fetch
    -0.68
    ázat
    -0.67
     tins
    -0.67
     потрібно
    -0.67
    IDX
    -0.67
     centimeters
    -0.66
     shrimp
    -0.66
     Publications
    -0.66
    POSITIVE LOGITS
    ABS
    0.93
     ABS
    0.82
    ABI
    0.81
    BTN
    0.78
    BPF
    0.77
    hatic
    0.75
     Evansville
    0.74
    颚
    0.71
    PII
    0.71
     abs
    0.70
    Activations Density 0.013%

    No Known Activations