© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32890
    Prev
    Next
    INDEX
    Explanations

    `_mm_` prefix, types, common words

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

    This neuron responds to C/C++ header‐include directives (the `#include "…"`) 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_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
     no
    -1.21
     Even
    -1.17
     not
    -1.16
     even
    -1.14
     only
    -1.14
     by
    -1.08
     additional
    -1.07
     on
    -1.06
    諳
    -1.05
     nestled
    -1.02
    POSITIVE LOGITS
     podrán
    1.20
     Dinas
    1.13
     родствен
    1.09
     boister
    1.08
     QUICK
    1.08
    מיש
    1.05
     två
    1.05
     frequentemente
    1.04
     prenn
    1.02
     piensan
    0.99
    Activations Density 0.010%

    No Known Activations