© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109477
    Prev
    Next
    INDEX
    Explanations

    aut, auto, intr, autom

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

    The neuron detects occurrences of Latin‐derived scientific/technical prefixes—particularly “aut(o)” (as in autorun, autonym) and “intr(a)” (as in intron, intratympanic).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    برد
    -0.90
     御
    -0.78
    sipasi
    -0.76
     Scope
    -0.76
     bios
    -0.74
     FLOOD
    -0.73
    ねー
    -0.73
     Adding
    -0.69
     Tail
    -0.69
     los
    -0.68
    POSITIVE LOGITS
     admirably
    0.76
    ebaran
    0.72
    น้ำ
    0.72
     acciaio
    0.69
    aptation
    0.69
     enlargement
    0.69
    inflammation
    0.69
     admirable
    0.68
     handsomely
    0.68
    cens
    0.67
    Activations Density 0.080%

    No Known Activations