© 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. 34-GEMMASCOPE-RES-131K
    7. 79221
    Prev
    Next
    INDEX
    Explanations

    java code processing data

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

    The neuron is sensitive to numeric tokens, i.e. literal numbers in the text (integer constants).

    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
    Folks
    -1.21
     :
    -1.17
     ;-)
    -1.16
    强大
    -1.13
     :-(
    -1.11
     nedeniyle
    -1.10
     aprecia
    -1.09
    　　*
    -1.08
    Variante
    -1.07
     löytyy
    -1.07
    POSITIVE LOGITS
    1.31
    ofla
    1.18
     

    1.13
     ArrayList
    1.09
    {\
    1.09
     boolean
    1.08
     String
    1.06
    java
    1.03
     made
    1.03
     set
    1.03
    Activations Density 0.705%
    No Known Activations