© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10486
    Prev
    Next
    INDEX
    Explanations

    fractions and measurements

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

    This neuron specializes in spotting advisory or prescriptive language—words and phrases that convey recommendations, conditions, or guidance (e.g., should, alternative, bear in mind, in case, may).

    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
    ﯾ
    0.59
    لمات
    0.53
    क्षक
    0.53
    στ
    0.52
    MING
    0.52
    લ્
    0.50
    ئ
    0.50
    ﺷ
    0.50
    𝘄
    0.50
    natal
    0.50
    POSITIVE LOGITS
     quantified
    0.60
     Gann
    0.57
     Ober
    0.57
     sejak
    0.57
     Mecklenburg
    0.57
     Gemeinde
    0.56
     Depuis
    0.56
     irritation
    0.56
    ².
    0.56
     אך
    0.56
    Activations Density 0.538%

    No Known Activations