© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15497
    Prev
    Next
    INDEX
    Explanations

    without reinstalling or multiple

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

    The neuron detects floating-point numbers (numerical tokens with decimals).

    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
    ס
    0.90
    ن
    0.88
    ун
    0.85
    Política
    0.79
    מס
    0.77
    लु
    0.72
    ר
    0.72
    አ
    0.71
     staw
    0.71
     rì
    0.70
    POSITIVE LOGITS
     then
    0.82
     oddly
    0.82
     was
    0.82
     immediately
    0.79
     the
    0.78
     so
    0.77
     into
    0.76
     at
    0.76
     on
    0.75
     inside
    0.75
    Activations Density 0.000%

    No Known Activations