© 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. 23707
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

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

    programming or code-related content, particularly numeric values and special characters in structured text.

    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
     striped
    -0.87
    VERSION
    -0.84
     Furcht
    -0.82
     Obviously
    -0.79
     tqdm
    -0.77
     ит
    -0.75
    ற
    -0.74
    ariant
    -0.73
     aggravated
    -0.71
     fenders
    -0.71
    POSITIVE LOGITS
     projekty
    0.88
     municípios
    0.87
    zade
    0.84
     ธ
    0.84
     桜
    0.83
    ův
    0.82
    輦
    0.80
    Wait
    0.79
    CAB
    0.78
    нечно
    0.78
    Activations Density 0.002%

    No Known Activations