© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86127
    Prev
    Next
    INDEX
    Explanations

    declaring types or members

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

    The neuron fires on code‐style identifier fragments (e.g. “decl”, “thunk”, “Dele”) rather than ordinary English words.

    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
     \
    -2.64
     \&
    -2.55
    ↵
    -2.52
     To
    -2.45
    ’,
    -2.28
    "
    -2.27
    筴
    -2.11
    <
    -2.08
     werden
    -2.06
    玙
    -2.06
    POSITIVE LOGITS
    ното
    2.53
     utilizzato
    2.30
    毉
    2.27
    ꯱
    2.23
     駅前
    2.17
     suoi
    2.14
     såg
    2.13
    用
    2.13
     تصوير
    2.13
     ----------
    2.13
    Activations Density 0.005%

    No Known Activations