© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6859
    Prev
    Next
    INDEX
    Explanations

    yaml kind metadata

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

    This neuron spotlights the boilerplate blog‐post footer about subscribing via RSS (e.g. “You can follow any responses to this entry through the RSS 2.0 feed”).

    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_31_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
     Acknowledg
    0.62
     listop
    0.59
    
    0.58
     Bona
    0.57
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.56
    sendFile
    0.55
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.53
    ोग
    0.52
     progressively
    0.52
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.52
    POSITIVE LOGITS
    ákat
    0.60
     линий
    0.59
     カ
    0.57
    emat
    0.57
    Como
    0.56
     банк
    0.55
    unków
    0.55
    ták
    0.55
    как
    0.54
     সড়ক
    0.54
    Activations Density 0.001%

    No Known Activations