© 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. 34649
    Prev
    Next
    INDEX
    Explanations

    attribution and authorship claims

    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
     our
    -1.04
    録画
    -1.02
     leaders
    -1.01
     Thomas
    -0.99
     leader
    -0.99
     familiar
    -0.99
    Ẓ
    -0.99
     N
    -0.98
     look
    -0.96
     Sam
    -0.96
    POSITIVE LOGITS
    ocrats
    1.16
    designed
    1.13
     созда
    1.13
    intended
    1.09
     creators
    1.08
    creator
    1.08
     paramètres
    1.06
     DataGridView
    1.05
     vendre
    1.04
     sjø
    1.04
    Activations Density 0.059%

    No Known Activations