© 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. 33509
    Prev
    Next
    INDEX
    Explanations

    acute toxicity followed by numbers

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

    scientific terminology related to organisms, species, and biological studies.

    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
     depar
    -0.87
     mice
    -0.78
     Bonaparte
    -0.77
     delegate
    -0.73
     gesam
    -0.72
     males
    -0.72
     male
    -0.70
     uống
    -0.69
    这家伙
    -0.68
     argues
    -0.67
    POSITIVE LOGITS
    liert
    0.82
     તે
    0.80
    ěř
    0.78
    ACON
    0.78
     \%,
    0.75
     static
    0.74
    layın
    0.73
     inspiré
    0.73
    bral
    0.73
    angolo
    0.73
    Activations Density 0.015%

    No Known Activations