© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3377
    Prev
    Next
    INDEX
    Explanations

    ASCII diagram structure

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

    The neuron is detecting newline characters (line breaks).

    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
    the
    1.02
    div
    0.84
    thesis
    0.82
    arching
    0.81
    edel
    0.81
    tem
    0.80
    have
    0.80
    ア
    0.79
    tilde
    0.77
    angg
    0.77
    POSITIVE LOGITS
     bienn
    0.79
     debts
    0.75
     sacraments
    0.71
     ventilators
    0.70
     consultations
    0.69
     proclam
    0.69
     lâu
    0.68
     compressors
    0.68
     spectrometers
    0.68
     gateways
    0.68
    Activations Density 0.000%

    No Known Activations