© 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. 65389
    Prev
    Next
    INDEX
    Explanations

    objective study threatening

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

    The main thing this neuron does is detect standalone numeric tokens (multi-digit numbers) 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
    memberOf
    -0.79
    ваемых
    -0.72
    ショ
    -0.71
    ⣾
    -0.69
    頼
    -0.69
    앙
    -0.68
     inhabitants
    -0.68
     Од
    -0.67
     Sele
    -0.66
     Wrong
    -0.66
    POSITIVE LOGITS
     ~=
    0.75
     אדם
    0.75
     Nutzen
    0.73
     equipamento
    0.73
    .}(
    0.71
    gantian
    0.71
     Nazar
    0.69
    rimidine
    0.69
     readership
    0.69
     nanos
    0.68
    Activations Density 0.014%

    No Known Activations