© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99179
    Prev
    Next
    INDEX
    Explanations

    words followed by specific words

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

    The neuron fires on numeric tokens (especially decimal or multi‐digit numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     our
    -1.73
     like
    -1.69
     also
    -1.68
     both
    -1.63
     such
    -1.63
     of
    -1.63
     this
    -1.60
     always
    -1.59
     every
    -1.52
     these
    -1.50
    POSITIVE LOGITS
    闐
    1.57
    
    1.56
    Oktober
    1.54
     renom
    1.52
    
    1.46
     markt
    1.45
     baden
    1.43
    СП
    1.43
     Polskiego
    1.41
     dezelve
    1.40
    Activations Density 0.502%

    No Known Activations