© 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. 12099
    Prev
    Next
    INDEX
    Explanations

    appreciation for

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

    This neuron detects numbered list or section headings marked by a digit and a period (e.g. “1.”) at the start of a line.

    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
    frigerator
    0.60
    borhood
    0.56
    的面
    0.55
    ósticos
    0.54
     diarias
    0.54
    镁
    0.54
    MgCl
    0.53
    铢
    0.53
     目前
    0.52
    ddots
    0.51
    POSITIVE LOGITS
     ach
    0.64
     en
    0.61
     Dale
    0.59
     NIKE
    0.57
     enh
    0.57
     Rosa
    0.55
     Monty
    0.55
     judgement
    0.54
     beggars
    0.54
     atro
    0.54
    Activations Density 0.000%

    No Known Activations