© 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. 22-GEMMASCOPE-RES-131K
    7. 92899
    Prev
    Next
    INDEX
    Explanations

    words that can begin phrases

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

    The neuron fires on commercial/transactional cues—numbers, units, and “buy”/“download”-style calls to action in sales-oriented text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     komfort
    -1.05
     kompati
    -1.05
     فقط
    -1.01
     komfor
    -1.01
     koncentr
    -1.00
     SYMBOL
    -0.96
     kabát
    -0.95
    flik
    -0.94
     objekt
    -0.93
    çok
    -0.93
    POSITIVE LOGITS
    ํา
    0.93
     as
    0.81
    zent
    0.79
     Rever
    0.76
    igerung
    0.75
     воз
    0.74
    记住
    0.72
     căng
    0.72
    stow
    0.71
     permettra
    0.70
    Activations Density 0.001%

    No Known Activations