© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79905
    Prev
    Next
    INDEX
    Explanations

    pros and cons

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

    The neuron detects headings or labels that introduce lists of advantages and disadvantages (e.g. “Pros,” “Cons,” “Advantages,” “Disadvantages”).

    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
     in
    -1.79
     to
    -1.66
     conforman
    -1.27
     diverso
    -1.20
     afectan
    -1.19
     indicate
    -1.17
     you
    -1.16
     provides
    -1.16
    ticiones
    -1.13
    abbix
    -1.13
    POSITIVE LOGITS
     and
    1.85
     lavable
    1.27
     propriétaires
    1.24
     calendriers
    1.23
     plastiques
    1.20
    Atlético
    1.19
     élimin
    1.19
     coûts
    1.17
     étan
    1.17
     réfrig
    1.14
    Activations Density 0.021%

    No Known Activations