© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32605
    Prev
    Next
    INDEX
    Explanations

    words related to problems or questions

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

    The neuron fires on meta‐text signals—words framing instructional or explanatory content (e.g. “notes,” “advice,” “objectives,” “instructions”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     every
    -1.29
     think
    -1.26
     corregir
    -1.19
     two
    -1.19
     县
    -1.16
    と思いました
    -1.14
     dozens
    -1.13
     three
    -1.13
    upra
    -1.10
    cabul
    -1.09
    POSITIVE LOGITS
    ícias
    1.54
    iramente
    1.42
    ighed
    1.41
    letics
    1.41
    swire
    1.37
    middels
    1.36
    itisation
    1.34
    
    1.32
    atization
    1.32
    ARON
    1.32
    Activations Density 0.022%

    No Known Activations