© 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. 22-GEMMASCOPE-RES-131K
    7. 34118
    Prev
    Next
    INDEX
    Explanations

    program identifiers and syntax

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

    The neuron is selectively activating on C/C++ pointer declarations—i.e. the '*' symbol (and its surrounding type name) in 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_22/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
    اگر
    -1.48
     their
    -1.38
     menikmati
    -1.28
     anything
    -1.26
     and
    -1.16
     melindungi
    -1.14
    是否
    -1.13
    orianCalendar
    -1.11
    Další
    -1.09
    zku
    -1.09
    POSITIVE LOGITS
    そういった
    1.22
    搅拌
    1.22
     engraçado
    1.14
     古い
    1.08
     ポーズ
    1.07
     τὸν
    1.05
    だからこそ
    1.02
     メニュー
    1.01
     impossível
    1.00
     Saludos
    0.97
    Activations Density 0.006%

    No Known Activations