© 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. 7808
    Prev
    Next
    INDEX
    Explanations

    English language texts

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

    This neuron fires on tokens immediately following numeric values or measurements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mid-sentence contexts

    np_max-act-logits · claude-4-5-sonnetTriggered by @jrosseruk
    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
    ſt
    0.78
     imágenes
    0.77
    ruciating
    0.76
    犮
    0.76
    arat
    0.74
    렸다
    0.74
    রবি
    0.72
    resistance
    0.71
    ⴱ
    0.71
    ście
    0.71
    POSITIVE LOGITS
     INVESTMENT
    0.88
    з
    0.83
    いない
    0.75
    nament
    0.74
    Funding
    0.73
    ком
    0.72
    ків
    0.72
    קה
    0.71
    نامه
    0.71
    ದ್ದ
    0.70
    Activations Density 0.000%

    No Known Activations