© 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. 50373
    Prev
    Next
    INDEX
    Explanations

    attribute value declarations

    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
     for
    -1.10
     at
    -0.98
     as
    -0.98
     or
    -0.98
     by
    -0.96
    衢
    -0.94
     Allah
    -0.93
     even
    -0.92
     made
    -0.91
     until
    -0.91
    POSITIVE LOGITS
     angep
    1.17
     gigantic
    1.14
     semejante
    1.11
     такая
    1.07
     angefü
    1.05
     wonderful
    1.05
     takiej
    1.04
     jednej
    1.04
     wondrous
    1.02
     pn
    0.99
    Activations Density 0.001%

    No Known Activations