© 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. 103165
    Prev
    Next
    INDEX
    Explanations

    help wanted

    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
     apostar
    -0.96
     cobrar
    -0.89
    jury
    -0.84
     verkau
    -0.77
     aluguel
    -0.77
     helped
    -0.77
    lures
    -0.77
    手術
    -0.75
    ukum
    -0.73
     regardant
    -0.73
    POSITIVE LOGITS
    desk
    1.68
     Wanted
    1.35
    wanted
    1.34
    fully
    1.25
     Desk
    1.21
     desk
    1.20
     wanted
    1.13
    fulness
    1.12
    Desk
    1.10
    Wanted
    1.06
    Activations Density 0.019%

    No Known Activations