© 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. 2816
    Prev
    Next
    INDEX
    Explanations

    finishly; entation; own

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

    The neuron selectively activates on longer, less frequent wordpiece tokens (multi-character fragments of words).

    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
     οποίο
    0.59
     deinem
    0.54
     οποία
    0.52
    𝗵
    0.52
     Ру
    0.52
     Sébastien
    0.52
     Puedes
    0.51
     μαύ
    0.50
     أغسطس
    0.50
     podrás
    0.50
    POSITIVE LOGITS
    .
    0.95
    ,
    0.80
    ↵
    0.70
    0
    0.56
    !
    0.54
    。
    0.52
     -
    0.50
    ..
    0.49
    ;
    0.48
      
    0.47
    Activations Density 0.001%

    No Known Activations