© 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. 115967
    Prev
    Next
    INDEX
    Explanations

    hair loss and styles

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

    The neuron strongly responds to content‐bearing words—especially multi‐syllable nouns and adjectives—rather than to common function words.

    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
     smelly
    -0.74
    keydown
    -0.74
    lofen
    -0.74
    elaar
    -0.73
    ผิด
    -0.73
    Stret
    -0.72
    Scrub
    -0.71
    Bras
    -0.71
    drm
    -0.69
    brigens
    -0.69
    POSITIVE LOGITS
     bangs
    1.72
     strands
    1.44
     strand
    1.28
    Bang
    1.26
     fringe
    1.16
     bang
    1.14
     Bang
    1.10
     parting
    1.09
    bang
    1.06
     фрон
    0.98
    Activations Density 0.012%

    No Known Activations