© 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. 69188
    Prev
    Next
    INDEX
    Explanations

    greetings and questions

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

    This neuron fires on standalone punctuation and formatting markers (e.g. commas, quotes, hyphens, angle brackets) and similar non-word tokens.

    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
    &__
    -1.34
    tagHelper
    -1.22
     />
    
    -1.19
    mathrm
    -1.18
     []:
    -1.17
    }
    
    -1.12
    });
    -1.10
     radians
    -1.09
     belajar
    -1.09
    />
    
    -1.09
    POSITIVE LOGITS
     this
    1.23
     it
    1.12
     but
    1.11
     noted
    1.03
     what
    0.99
    Kelebihan
    0.95
     ASSIST
    0.94
     also
    0.94
    кухня
    0.93
    ulents
    0.93
    Activations Density 0.004%

    No Known Activations