© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3617
    Prev
    Next
    INDEX
    Explanations

    false, FIELD, position

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

    The neuron is sensitive to integer literals (numeric constants) in the code.

    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
    ch
    -2.66
    "-
    -2.64
    \
    -2.58
    m
    -2.56
    ”.
    -2.48
    ll
    -2.39
    ),
    -2.31
    ”-
    -2.28
    )-
    -2.27
    no
    -2.20
    POSITIVE LOGITS
     There
    3.14
    釹
    2.69
     Есть
    2.31
    ribue
    2.28
     essayé
    2.28
     समीक्षाएं
    2.22
    苌
    2.22
    
    2.19
     apartamentos
    2.17
     صنعت
    2.16
    Activations Density 0.006%

    No Known Activations