© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 91
    Prev
    Next
    INDEX
    Explanations

    flow provides

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

    The neuron fires on capitalized named entities, especially organization names, countries, and political groups.

    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
    Result
    0.36
    Ди
    0.34
    <0x0D>
    0.33
    Category
    0.31
    ただし
    0.31
    Gaussian
    0.31
    Па
    0.30
    แต่
    0.29
     forKey
    0.29
    Exception
    0.29
    POSITIVE LOGITS
     knows
    0.59
     prides
    0.57
     hasn
    0.55
     owes
    0.55
    ’
    0.55
     possesses
    0.55
    வின்
    0.54
     యొక్క
    0.54
     spends
    0.53
     has
    0.53
    Activations Density 1.045%

    No Known Activations