© 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. 3022
    Prev
    Next
    INDEX
    Explanations

    in this case / at its heart

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

    This neuron fires on phrases that start with “In this” when introducing a section or example (e.g. “In this therapy,” “In this short video,” “In this page,” etc.).

    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
     aldığı
    0.66
     σε
    0.63
     ու
    0.61
    []');
    0.61
    )');
    0.60
     имущества
    0.60
     в
    0.59
     !='')
    0.59
     β
    0.58
    یف
    0.58
    POSITIVE LOGITS
     ،
    0.77
    *,
    0.73
    (),
    0.72
    
    0.71
    ،
    0.70
    ፣
    0.70
    $,
    0.69
     nutshell
    0.68
    ，
    0.68
    twist
    0.67
    Activations Density 0.277%

    No Known Activations