© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11306
    Prev
    Next
    INDEX
    Explanations

    urls and domain names

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

    This neuron activates on numeric tokens (including numbers, decimals, and percentage values).

    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
    ఞ
    0.44
     ..............
    0.43
    ába
    0.42
    ൪
    0.42
    óticos
    0.42
    ৤
    0.41
    organiser
    0.40
     ……..
    0.40
    °;
    0.39
    ást
    0.39
    POSITIVE LOGITS
    <unused61>
    0.36
    -
    0.35
    }
    0.33
     both
    0.33
     text
    0.33
     this
    0.32
     math
    0.32
     =
    0.32
    /
    0.32
    ,
    0.32
    Activations Density 0.019%

    No Known Activations