© 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. 35459
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
     without
    -2.52
     as
    -2.47
     not
    -2.42
     at
    -2.36
     undeniably
    -2.33
     before
    -2.25
     Despite
    -2.20
     two
    -2.20
     Creating
    -2.17
     only
    -2.13
    POSITIVE LOGITS
     Dinas
    2.28
     delightfully
    2.17
     horrid
    2.09
    generally
    2.02
     faciliter
    2.00
     deliciously
    1.99
     ludicrous
    1.97
     momentous
    1.94
     revamped
    1.94
     dismal
    1.91
    Activations Density 0.021%

    No Known Activations