© 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. 91074
    Prev
    Next
    INDEX
    Explanations

    technical and safety information

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ährlich
    -0.79
     Crescent
    -0.77
    JAH
    -0.71
    houding
    -0.70
     آذ
    -0.69
     sembler
    -0.69
     年代
    -0.68
     Richards
    -0.68
    pubs
    -0.67
     muzzle
    -0.66
    POSITIVE LOGITS
     toxicological
    0.90
     Toxicological
    0.86
     TRANSPORT
    0.84
     transport
    0.83
    posure
    0.82
     Numerade
    0.81
     exposure
    0.81
     reactivity
    0.81
     disposal
    0.80
     ১
    0.80
    Activations Density 0.005%

    No Known Activations