© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113560
    Prev
    Next
    INDEX
    Explanations

    public followed by class names

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

    the keyword "public" in code, particularly in class inheritance declarations and access specifiers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of the C++ access specifier “public” (e.g. in class inheritance or member‐access 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_10/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
     
    -2.50
    ↵↵↵
    -2.16
    2
    -1.70
    1
    -1.69
     be
    -1.66
     ‘
    -1.66
    </strong>
    -1.63
    ↵↵
    -1.63
     then
    -1.63
    );
    -1.61
    POSITIVE LOGITS
    ementara
    2.25
     and
    2.11
    ୌ
    2.05
     reklama
    1.91
     aksesuar
    1.81
     besos
    1.77
     APPELLATE
    1.76
     kompati
    1.74
    rozum
    1.74
    leicht
    1.73
    Activations Density 0.000%

    No Known Activations