© 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. 22-GEMMASCOPE-RES-131K
    7. 27141
    Prev
    Next
    INDEX
    Explanations

    C++ code function names

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

    The neuron fires on C standard‐library identifiers—names of headers and library functions.

    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
     mereka
    -1.34
    ...-
    -1.30
     dve
    -1.19
     Olympedia
    -1.19
    纐
    -1.17
     più
    -1.16
     mehr
    -1.15
    他们
    -1.12
    ningar
    -1.10
     spielte
    -1.09
    POSITIVE LOGITS
     it
    1.82
     at
    1.52
    acakt
    1.27
     that
    1.20
     trembling
    1.18
    It
    1.05
     combustível
    1.00
    緋
    1.00
    taje
    1.00
    cyklo
    0.99
    Activations Density 0.014%

    No Known Activations