© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77723
    Prev
    Next
    INDEX
    Explanations

    air pollution, ground water, surface sediments, Soviet prisoners

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

    environmental pollution and contamination terms.

    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
    ExternalTask
    -0.94
     discovered
    -0.94
     கி
    -0.87
    Լ
    -0.85
    Materiales
    -0.84
     discover
    -0.82
     how
    -0.80
     possibly
    -0.80
    icznie
    -0.80
     perhaps
    -0.79
    POSITIVE LOGITS
    details
    0.95
    rizona
    0.91
    @#
    0.85
     SCHEME
    0.84
     デニム
    0.84
    
    0.83
    haling
    0.82
     WHEEL
    0.80
     amput
    0.80
     MINE
    0.80
    Activations Density 0.001%

    No Known Activations