© 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. 26520
    Prev
    Next
    INDEX
    Explanations

    programming constructs and types

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

    The neuron fires on C/C++ pointer type names and pointer declarations.

    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
     *
    -1.37
    1
    -1.23
    ®
    -1.17
     ^
    -1.16
    ?
    -1.06
    M
    -1.05
     S
    -1.05
     ·
    -1.04
    N
    -1.02
    2
    -0.98
    POSITIVE LOGITS
    Nazwa
    1.17
    quando
    1.15
     作り方
    1.11
    ﮨ
    1.09
    🎣
    1.08
     alcool
    1.07
     millioner
    1.05
    ఈ
    1.05
     fruta
    1.05
     embl
    1.05
    Activations Density 0.007%

    No Known Activations