© 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. 94155
    Prev
    Next
    INDEX
    Explanations

    fitness programs and routines

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

    This neuron responds to tokens that are part of section or program titles—especially capitalized words, numbers, and punctuation (e.g. “Yoga,” “Secrets,” “2-week,” “Video Series,” “Workout2000”) characteristic of headings.

    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
     лъ
    -0.82
     Supports
    -0.81
    jedno
    -0.78
     STATEMENT
    -0.76
    odotus
    -0.73
     Statement
    -0.73
    vigil
    -0.72
     mascota
    -0.71
    考试
    -0.71
     river
    -0.71
    POSITIVE LOGITS
     plan
    1.22
     programs
    1.19
     program
    1.12
     routines
    1.10
     suggested
    1.08
     plans
    1.02
     challenges
    1.01
     routine
    1.00
     workouts
    0.99
     beginner
    0.97
    Activations Density 0.023%

    No Known Activations