© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72846
    Prev
    Next
    INDEX
    Explanations

    noun followed by a verb

    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
     on
    -2.53
     an
    -2.34
     at
    -2.27
     what
    -2.11
     with
    -2.11
     one
    -2.09
     from
    -2.09
     using
    -2.08
     their
    -2.08
     as
    -2.08
    POSITIVE LOGITS
     Dinas
    2.09
     overly
    1.95
    mainly
    1.94
    があり
    1.92
     goofy
    1.88
     horrid
    1.88
     delightfully
    1.85
     disgruntled
    1.85
     shimmering
    1.84
     famed
    1.81
    Activations Density 0.093%

    No Known Activations