© 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. 10-GEMMASCOPE-RES-131K
    7. 15491
    Prev
    Next
    INDEX
    Explanations

    specific token sequences

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

    The neuron fires on code API method names (e.g. camelCase function calls).

    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
     You
    -2.98
     The
    -2.64
     When
    -2.53
     What
    -2.25
     одна
    -2.23
    甦
    -2.22
     Hinblick
    -2.22
    ция
    -2.17
     Why
    -2.13
     It
    -2.03
    POSITIVE LOGITS
    ar
    2.58
    槩
    2.47
    ad
    2.45
    "",
    2.22
    ほうが
    2.22
    ﮯ
    2.20
    li
    2.19
    
    2.11
    ቫ
    2.03
    ﮩ
    2.00
    Activations Density 0.000%

    No Known Activations