© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5144
    Prev
    Next
    INDEX
    Explanations

    SMS handling

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

    This neuron detects occurrences of the word “match” (in any form such as “match,” “matches,” etc.).

    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
    u
    0.89
    ↵↵
    0.85
    にご
    0.82
    ST
    0.80
    ALITY
    0.77
    K
    0.75
    ES
    0.74
    W
    0.73
    Z
    0.73
     inherent
    0.72
    POSITIVE LOGITS
    𒊹
    0.96
     rey
    0.93
    বিভিন্ন
    0.93
    audioType
    0.90
     стаўкі
    0.87
    𝟐
    0.82
    пециа
    0.82
     ৮ম
    0.82
    varchar
    0.81
     гульнявыя
    0.80
    Activations Density 0.001%

    No Known Activations