© 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. 4285
    Prev
    Next
    INDEX
    Explanations

    equivalence signs ≡

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

    The neuron is highly sensitive to numeric tokens (i.e. digits).

    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
     reimag
    0.45
    Modal
    0.43
    ਸ
    0.41
     redesign
    0.40
    зовая
    0.40
     rethink
    0.40
     USAID
    0.40
    4
    0.39
    珺
    0.38
     Özel
    0.38
    POSITIVE LOGITS
     चांगले
    0.47
    MiddleLine
    0.43
     противополо
    0.43
     inexplicable
    0.42
     ইহাই
    0.41
     antagonism
    0.41
     inanimate
    0.41
     некоторое
    0.41
     certaine
    0.41
     स्वातंत्र्य
    0.41
    Activations Density 0.000%

    No Known Activations