© 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. 4282
    Prev
    Next
    INDEX
    Explanations

    the Beach Boys and surfing

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

    The neuron primarily detects numeric tokens (numbers or number-like strings).

    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
     spiders
    -0.84
     naam
    -0.73
     REED
    -0.71
     Spiders
    -0.69
    ModelAndView
    -0.68
     establishments
    -0.66
     недели
    -0.66
     Ansari
    -0.65
     totalCount
    -0.65
     Basso
    -0.65
    POSITIVE LOGITS
     Beach
    1.36
    Beach
    1.26
     BEACH
    1.09
     Surfer
    1.07
     Brian
    1.02
    beach
    0.98
     beach
    0.98
    Surf
    0.96
     surfboard
    0.95
     Pet
    0.95
    Activations Density 0.020%

    No Known Activations