© 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. 9461
    Prev
    Next
    INDEX
    Explanations

    fear and worry

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

    The neuron primarily detects words expressing fear or anxiety.

    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
    stub
    0.58
    argate
    0.58
    Dig
    0.56
    醉
    0.56
     Guel
    0.56
    dig
    0.54
    ハマ
    0.52
    亼
    0.52
    aidl
    0.52
     Forge
    0.51
    POSITIVE LOGITS
     fear
    3.56
     fears
    3.39
     Fear
    3.13
    fear
    3.13
     fearful
    3.09
    Fear
    3.09
     miedo
    3.00
     worry
    2.98
     Fears
    2.97
     worries
    2.94
    Activations Density 0.789%

    No Known Activations