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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14973
    Prev
    Next
    INDEX
    Explanations

    Retrieval, Evidence, Q, Conversations

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

    The neuron activates on standalone numeric tokens (numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    origami
    -1.81
    motorola
    -1.65
    collage
    -1.63
    redmi
    -1.54
    chalet
    -1.53
    bouquet
    -1.53
    ᐕ
    -1.52
    镠
    -1.51
    nissan
    -1.50
    로그인
    -1.50
    POSITIVE LOGITS
    3
    2.13
    a
    2.09
    0
    2.02
     also
    1.95
    1
    1.84
     
    1.79
    4
    1.66
     want
    1.62
    2
    1.62
    as
    1.61
    Activations Density 0.000%

    No Known Activations