© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77406
    Prev
    Next
    INDEX
    Explanations

    setter and related code

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

    The neuron fires on tokens containing multi‐digit numbers or version‐style numeric literals.

    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
     get
    -1.02
     getting
    -0.90
     additional
    -0.90
    ကိုးကား
    -0.87
     gets
    -0.82
     ((
    -0.81
     εφαρ
    -0.79
     begin
    -0.77
     implementing
    -0.77
     Additional
    -0.76
    POSITIVE LOGITS
     setters
    1.25
     setter
    1.23
     설정
    1.00
    often
    0.99
    Bjs
    0.94
     errichtet
    0.93
    setter
    0.93
     solches
    0.93
    rodow
    0.92
     BRIEF
    0.92
    Activations Density 0.001%

    No Known Activations