© 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. 31-GEMMASCOPE-2-RES-16K
    4. 15685
    Prev
    Next
    INDEX
    Explanations

    crisis text line

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

    The neuron specifically activates on floating-point numeric values (i.e. decimal numbers).

    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
    estyle
    0.63
    莆
    0.57
    すぎて
    0.56
    〒
    0.55
    過ぎ
    0.54
    装備
    0.53
    ❷
    0.53
    ημ
    0.52
    الج
    0.52
    صب
    0.52
    POSITIVE LOGITS
     Astrophysics
    0.58
     embarrassment
    0.57
     dismay
    0.57
     Colonel
    0.56
     envy
    0.56
     desh
    0.55
    ichter
    0.54
     Lonely
    0.54
    亮
    0.54
     lanes
    0.54
    Activations Density 0.009%

    No Known Activations