© 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. 32943
    Prev
    Next
    INDEX
    Explanations

    code tokens and identifiers

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

    This neuron overwhelmingly fires on C/C++ function parameters or variable declarations involving the pointer symbol “*,” i.e. 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
    は
    -1.31
    isfile
    -1.20
    6
    -1.17
    を
    -1.16
    7
    -1.16
    が
    -1.12
    8
    -1.11
    がありますが
    -1.07
    vitis
    -1.05
    ulage
    -1.05
    POSITIVE LOGITS
    ところに
    1.24
     mengenakan
    1.23
    unción
    1.13
    egli
    1.13
    ására
    1.09
    tentu
    1.09
    なのかな
    1.08
     «<
    1.07
    قامت
    1.06
     opak
    1.05
    Activations Density 0.007%

    No Known Activations