© 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. 9402
    Prev
    Next
    INDEX
    Explanations

    how ... extreme

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

    The neuron primarily detects floating-point numeric tokens (numbers containing a decimal point).

    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
     reload
    0.66
    Data
    0.64
    Input
    0.64
    a
    0.62
     data
    0.60
    Use
    0.60
    '.
    0.59
    ADD
    0.58
    '+
    0.58
     Use
    0.58
    POSITIVE LOGITS
     possíveis
    0.81
     चेंजेस
    0.79
     μπορεί
    0.78
    genos
    0.77
     inferiores
    0.77
     Badajoz
    0.76
    icznej
    0.75
    <unused52>
    0.75
     terület
    0.75
     Zeitschr
    0.74
    Activations Density 0.001%

    No Known Activations