© 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. 39033
    Prev
    Next
    INDEX
    Explanations

    android widget or app

    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
     from
    -2.38
     by
    -2.34
     at
    -2.27
     through
    -2.16
     which
    -2.08
     and
    -2.08
     both
    -2.08
     their
    -2.05
     with
    -2.00
     every
    -1.99
    POSITIVE LOGITS
     gigantic
    1.80
     wondrous
    1.79
     unending
    1.74
     horrid
    1.70
     hefty
    1.63
     marvelous
    1.62
     enraged
    1.61
     sooo
    1.60
     soooo
    1.59
     luscious
    1.59
    Activations Density 0.003%

    No Known Activations