© 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. 13489
    Prev
    Next
    INDEX
    Explanations

    haiku

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

    The neuron fires on numeric tokens—especially decimal‐point numbers or large numeric measurements.

    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
     Vậy
    0.95
    Isn
    0.83
    Vậy
    0.81
     vậy
    0.77
    InputStream
    0.75
     Sélectionnez
    0.74
    क
    0.74
     Cheers
    0.73
    ܘܢ
    0.71
    u
    0.71
    POSITIVE LOGITS
     moldings
    0.73
    عرِّف
    0.68
     produkt
    0.66
    ภูมิ
    0.66
     megfelel
    0.65
     bores
    0.64
    能够在
    0.64
    ’),
    0.63
    ຜະລິດຕະພັນ
    0.63
     transcribe
    0.63
    Activations Density 0.000%

    No Known Activations