© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3609
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

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

    The neuron detects floating-point numeric literals (numbers with decimal points) embedded in code or data.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    이고
    0.92
    או
    0.84
    ❖
    0.83
    
    0.82
    ic
    0.80
    פ
    0.76
    ح
    0.76
    이나
    0.75
    ა
    0.75
    ם
    0.75
    POSITIVE LOGITS
     '')
    0.95
     []);
    0.94
    )}')
    0.93
     "");
    0.89
    ),'
    0.88
    )*
    0.87
     [])
    0.87
    );
    0.85
    )-\
    0.85
    )<
    0.85
    Activations Density 0.001%

    No Known Activations