© 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. 15063
    Prev
    Next
    INDEX
    Explanations

    dhal, pink, dog

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

    The neuron responds specifically to numeric tokens containing decimal points (floating-point numbers).

    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
    i
    0.93
     Monday
    0.80
     HOT
    0.78
    言う
    0.77
     Tuesday
    0.76
     JUAN
    0.76
     esperamos
    0.75
     Thursday
    0.75
     our
    0.75
    ings
    0.74
    POSITIVE LOGITS
    Ƭ
    0.86
    Β
    0.84
    Ре
    0.79
    Cheerful
    0.77
    Ү
    0.76
    Ε
    0.72
    杈
    0.72
    Pricing
    0.71
    Ұ
    0.71
    Έ
    0.71
    Activations Density 0.000%

    No Known Activations