© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8502
    Prev
    Next
    INDEX
    Explanations

    covering various aspects

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

    This neuron responds to relatively rare, multi-syllable content words—i.e. uncommon vocabulary with higher information content.

    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
    barcode
    0.89
    🆓
    0.80
    KF
    0.77
    homme
    0.77
    🥈
    0.77
    hapi
    0.75
    แรม
    0.75
    yang
    0.74
    keras
    0.74
    QFont
    0.74
    POSITIVE LOGITS
    Он
    0.86
     trolling
    0.78
    永
    0.76
     แชร์
    0.75
     ノ
    0.73
     counselling
    0.72
     auraient
    0.72
    ла
    0.71
     ダイニング
    0.71
    ون
    0.71
    Activations Density 0.000%

    No Known Activations