© 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. 70112
    Prev
    Next
    INDEX
    Explanations

    medium.com articles and plasmonics

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

    The neuron fires on named external‐resource tokens—i.e. domain names (like “medium”), file names/extensions (like “hpp,” “h”), and other tech‐resource 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
    ills
    -0.80
    CRYPT
    -0.76
    Happy
    -0.72
    cillos
    -0.69
     questionnaire
    -0.69
    reset
    -0.68
     美術
    -0.68
     செய
    -0.67
    Push
    -0.67
     süre
    -0.67
    POSITIVE LOGITS
     δι
    0.70
     TEMPO
    0.68
     allotted
    0.67
     Malte
    0.67
    ZONE
    0.66
     allocated
    0.66
     afforded
    0.65
    IMAGES
    0.65
    ticia
    0.64
    Cathy
    0.64
    Activations Density 0.057%

    No Known Activations