© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6684
    Prev
    Next
    INDEX
    Explanations

    state functions

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

    The neuron detects precise numeric tokens—i.e. floating-point numbers with decimal points.

    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
     mancanza
    0.93
     言っ
    0.88
    و
    0.88
     inglese
    0.87
     interdit
    0.86
     Qualquer
    0.85
     Sebelum
    0.84
     mistakenly
    0.84
    ים
    0.84
     উর্দু
    0.82
    POSITIVE LOGITS
    (
    0.93
    t
    0.85
    {
    0.81
    ((
    0.73
    \}
    0.72
    enden
    0.71
    ↵↵
    0.70
    }
    0.68
    </tbody>
    0.68
    回復
    0.67
    Activations Density 0.000%

    No Known Activations