© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15808
    Prev
    Next
    INDEX
    Explanations

    int (number of epochs/estimators)

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

    The neuron detects specific time‐of‐day expressions, especially afternoon times marked with “p.m.”.

    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
    દાર
    0.84
     cytoskeleton
    0.82
    ૯
    0.77
    𝔂
    0.77
    হি
    0.76
    ภั
    0.76
    ັດ
    0.75
    ከት
    0.75
     گئے
    0.74
     cinese
    0.73
    POSITIVE LOGITS
    آمد
    0.80
    stit
    0.80
    rega
    0.79
    ées
    0.75
    ங்கிணை
    0.74
     отношений
    0.73
    reserv
    0.71
     señal
    0.70
    뎁
    0.70
    POD
    0.70
    Activations Density 0.000%

    No Known Activations