© 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. 3398
    Prev
    Next
    INDEX
    Explanations

    code snippets or commands

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

    This neuron fires strongly on named entities (proper nouns) and numeric tokens.

    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
    (),
    0.81
    ,
    0.78
    】,
    0.76
    +,
    0.74
    *,
    0.73
    ،
    0.70
    -,
    0.68
    /
    0.67
    ),
    0.66
    ፣
    0.66
    POSITIVE LOGITS
     youll
    0.87
     nbsp
    0.87
     Although
    0.85
    そして
    0.85
     тобто
    0.82
     todays
    0.82
     Perhaps
    0.81
     etcétera
    0.81
     However
    0.80
     albeit
    0.79
    Activations Density 0.234%

    No Known Activations