© 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. 885
    Prev
    Next
    INDEX
    Explanations

    the

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

    The neuron strongly activates on numeric tokens and digit sequences (e.g. measurements, dimensions, quantities).

    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
    îtes
    0.56
    iftoire
    0.56
    ǜ
    0.55
    agaman
    0.55
    èves
    0.53
    aktionen
    0.53
    álogo
    0.52
    राकी
    0.51
    řízení
    0.50
    apadani
    0.50
    POSITIVE LOGITS
    .
    0.73
     the
    0.68
     this
    0.63
    )
    0.61
     other
    0.60
    ↵
    0.58
    ,
    0.58
     both
    0.57
     .
    0.54
     which
    0.54
    Activations Density 0.299%

    No Known Activations