© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14886
    Prev
    Next
    INDEX
    Explanations

    positional encodings

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

    This neuron primarily responds to numeric expressions and measurements (especially floating-point numbers).

    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
     tailored
    0.84
     favorite
    0.78
     Avatar
    0.75
     Vatican
    0.71
     conspiring
    0.71
    б
    0.71
     Lila
    0.70
     bipartisan
    0.68
     minst
    0.68
     oleks
    0.68
    POSITIVE LOGITS
    r
    1.13
    trunc
    1.05
    uncertain
    0.99
    ์
    0.95
    examples
    0.94
    algorithms
    0.93
    s
    0.93
    html
    0.93
    different
    0.93
    gaming
    0.93
    Activations Density 0.001%

    No Known Activations