© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130481
    Prev
    Next
    INDEX
    Explanations

    contracts or WIFI

    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_22/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
     furia
    -1.02
     enorme
    -1.02
     hybride
    -1.01
    矗
    -0.95
     revolu
    -0.95
    を購入
    -0.94
    āng
    -0.93
     minuter
    -0.92
     dager
    -0.92
     rigide
    -0.92
    POSITIVE LOGITS
     unless
    1.23
     or
    1.17
     any
    1.13
     except
    1.12
     first
    1.02
     those
    1.02
    hotra
    1.02
     either
    1.01
     daarbij
    1.00
     oraz
    0.99
    Activations Density 0.096%

    No Known Activations