© 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. 2879
    Prev
    Next
    INDEX
    Explanations

    Interface Version

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

    The neuron fires strongly on distinctive subword fragments of product and brand names (e.g. “OP,” “KA,” “xy,” “sn,” “HM,” “x,” “te”).

    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
     sAlarm
    0.56
     '.</
    0.56
     ListTile
    0.55
     irgende
    0.53
     ReturnVal
    0.52
     sentimento
    0.52
    :'],
    0.51
     QuantityOnHand
    0.51
     Zusammenhang
    0.51
     serde
    0.51
    POSITIVE LOGITS
     B
    0.52
     USA
    0.50
     platform
    0.49
     Oasis
    0.49
    ™
    0.49
     turnkey
    0.48
     F
    0.48
    全新
    0.48
    -
    0.48
     fully
    0.48
    Activations Density 0.001%

    No Known Activations