© 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. 102572
    Prev
    Next
    INDEX
    Explanations

    missile guidance systems

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

    The neuron specializes in detecting numeric tokens (digits or multi‐digit numbers) wherever they appear.

    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
     condado
    -0.90
     Gün
    -0.84
    Semoga
    -0.82
     Pendant
    -0.82
     Firearms
    -0.81
     partisan
    -0.76
     siècle
    -0.73
    теро
    -0.72
     gunshot
    -0.72
     anniversaire
    -0.71
    POSITIVE LOGITS
     guidance
    1.22
     Guidance
    1.19
     seeker
    1.10
     launch
    1.07
    Guidance
    1.02
     guides
    0.94
    launch
    0.93
     guiding
    0.88
    guidance
    0.84
     Guid
    0.82
    Activations Density 0.026%

    No Known Activations