© 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. 66271
    Prev
    Next
    INDEX
    Explanations

    dealing with or assisting

    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
     Adresse
    -0.75
     depositing
    -0.75
    Deposit
    -0.75
     Deposit
    -0.74
     আ
    -0.74
     Stephan
    -0.74
     zaidi
    -0.72
    fören
    -0.72
     kaž
    -0.72
    fır
    -0.72
    POSITIVE LOGITS
     help
    1.14
     handles
    1.08
     personally
    1.06
     handle
    1.00
     assist
    0.89
    handle
    0.85
     erv
    0.84
    umbered
    0.84
     helm
    0.84
    tamentos
    0.84
    Activations Density 0.008%

    No Known Activations