© 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. 13096
    Prev
    Next
    INDEX
    Explanations

    6 Silver

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

    This neuron detects date-related tokens (e.g. month names and adjoining day/year numerals).

    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
    ↵↵
    0.76
    }:
    0.58
    `:
    0.57
    ↵
    0.55
    ：
    0.55
    0
    0.53
    ():
    0.52
    :}
    0.52
    .:
    0.51
    L
    0.51
    POSITIVE LOGITS
     geriatric
    0.62
     photocatal
    0.57
     quilting
    0.57
     streetwear
    0.55
     ageing
    0.53
     yaşayan
    0.53
     penilaian
    0.52
     cricketer
    0.52
     yaşad
    0.52
     talla
    0.51
    Activations Density 0.025%

    No Known Activations