© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 464
    Prev
    Next
    INDEX
    Explanations

    colors in code

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

    The neuron is detecting single‐quote characters that mark the start of quoted sections.

    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
    ,
    0.40
    adays
    0.29
    ​,
    0.29
     Wix
    0.28
     theyre
    0.28
    ıma
    0.28
     exclusives
    0.28
     gets
    0.28
     dahil
    0.28
    ,*/}
    0.28
    POSITIVE LOGITS
     zapro
    0.33
    Physics
    0.30
    参数向量
    0.29
    Laboratory
    0.28
    Պ
    0.27
    mathcal
    0.26
    textsc
    0.26
    Parameters
    0.26
     Laboratory
    0.26
    Research
    0.26
    Activations Density 0.001%

    No Known Activations