© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77804
    Prev
    Next
    INDEX
    Explanations

    hair styling accessory

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

    The neuron fires on named entities and terminology – in particular proper nouns, brand/product names, and other key technical identifiers.

    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
    ₂,
    -0.87
     contraseña
    -0.80
    zzino
    -0.78
    jście
    -0.78
    Washing
    -0.75
     wicker
    -0.75
     ciclismo
    -0.75
    dued
    -0.73
    ofday
    -0.73
    ->$
    -0.72
    POSITIVE LOGITS
     salon
    1.16
     keratin
    1.02
     styling
    0.96
     barrels
    0.95
     curl
    0.94
     tourmaline
    0.94
     ceramic
    0.88
     barrel
    0.88
     salons
    0.87
     Ceramic
    0.86
    Activations Density 0.005%

    No Known Activations