© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6099
    Prev
    Next
    INDEX
    Explanations

    { or },

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

    The neuron activates on four-digit numeric tokens (e.g. years or large page/reference numbers) in bibliographic or citation contexts.

    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
    ،
    0.73
    ,
    0.66
    、
    0.61
     eigene
    0.55
     दें
    0.55
     altijd
    0.55
    、（
    0.55
    ፣
    0.55
    த்தார்
    0.54
     propri
    0.53
    POSITIVE LOGITS
    ()),
    1.42
    ),
    1.38
    _),
    1.30
    '),
    1.29
     ""),
    1.27
     '),
    1.22
    "),
    1.20
     ),
    1.19
    !),
    1.18
     ''),
    1.18
    Activations Density 0.059%

    No Known Activations