© 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. 25693
    Prev
    Next
    INDEX
    Explanations

    National Register of Historic Places listings

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

    The neuron activates on numeric tokens—especially multi‐digit year values (dates) and other numbers embedded in the text.

    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
    four
    -0.74
     ulo
    -0.73
    ≃
    -0.70
     Kisses
    -0.66
    FOUR
    -0.63
    キス
    -0.63
    ⁴
    -0.63
    zian
    -0.62
    initialization
    -0.62
    leur
    -0.62
    POSITIVE LOGITS
     bullpen
    0.66
    cloak
    0.65
    гни
    0.65
    styp
    0.63
    endiente
    0.63
    Edmund
    0.61
    DbContext
    0.61
    MUS
    0.60
     useRef
    0.60
    มือ
    0.60
    Activations Density 0.081%

    No Known Activations