© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76591
    Prev
    Next
    INDEX
    Explanations

    titles or roles like doctor

    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
    velo
    -0.77
    Fastest
    -0.73
    Hatch
    -0.73
     сан
    -0.69
     lamp
    -0.68
     employé
    -0.68
    ชี
    -0.67
     fotografii
    -0.67
    faster
    -0.67
     Hatch
    -0.67
    POSITIVE LOGITS
     Vandal
    0.87
     dosing
    0.80
     Tote
    0.74
    វ
    0.74
     Sacchar
    0.73
     artifact
    0.73
    ບ
    0.71
    ニュース
    0.69
     stairway
    0.68
     greco
    0.68
    Activations Density 0.029%

    No Known Activations