© 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. 34-GEMMASCOPE-RES-131K
    7. 58280
    Prev
    Next
    INDEX
    Explanations

    code syntax & operators

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

    This neuron identifies C/C++ pointer expressions—specifically pointer variable declarations, assignments, and uses (e.g., “*ptr = vec.data()”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     этих
    -0.77
     único
    -0.77
    alas
    -0.73
     oben
    -0.72
    gania
    -0.71
    wc
    -0.71
    ския
    -0.71
    chemise
    -0.70
    larg
    -0.70
    deln
    -0.70
    POSITIVE LOGITS
     &(
    1.36
    &(
    1.07
     &
    0.90
    )}+
    0.85
     sureties
    0.85
     addition
    0.82
    }+
    0.81
    )+\
    0.81
     $\&$
    0.81
    (&(
    0.81
    Activations Density 0.003%

    No Known Activations