© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107451
    Prev
    Next
    INDEX
    Explanations

    words like cycle, cyclo, cyano, cyborg

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

    chemical compounds and molecular structures containing 'cy' syllable prefix.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ствовали
    -0.73
     recently
    -0.72
    ționale
    -0.70
     stretch
    -0.70
    essed
    -0.68
     rarely
    -0.68
    ighters
    -0.67
     sometimes
    -0.67
    recent
    -0.67
     possível
    -0.66
    POSITIVE LOGITS
     ciclo
    1.20
     ци
    1.13
     Ци
    1.04
    Cycling
    1.03
     Cycle
    1.02
     cycles
    1.01
    Ци
    1.00
     cyclo
    0.98
     CYCLE
    0.97
     Cycles
    0.96
    Activations Density 0.074%

    No Known Activations