© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66201
    Prev
    Next
    INDEX
    Explanations

    fallout or radioactive contamination

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

    content related to radioactive fallout and contamination.

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

    The neuron activates on numeric tokens and numeric expressions (e.g., standalone numbers, hyphenated digits, and measurement values).

    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
    ູ
    -0.78
    Enclosure
    -0.74
     agentes
    -0.71
    lichung
    -0.69
    gefügt
    -0.69
    hicule
    -0.68
    gregor
    -0.68
     vayas
    -0.68
    Wai
    -0.66
    enddate
    -0.66
    POSITIVE LOGITS
     fall
    4.56
     fallout
    4.13
    fall
    3.63
    Fall
    3.25
     Fall
    3.25
    FALL
    3.02
     falling
    2.98
     FALL
    2.95
     Fallout
    2.83
    fallout
    2.80
    Activations Density 0.026%

    No Known Activations