© 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. 22-GEMMASCOPE-RES-131K
    7. 70640
    Prev
    Next
    INDEX
    Explanations

    offunding

    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
     at
    -2.56
     on
    -2.55
     when
    -2.34
     after
    -2.23
     before
    -2.17
     one
    -2.11
     from
    -2.08
     so
    -2.06
     all
    -2.06
     with
    -2.00
    POSITIVE LOGITS
     semelh
    2.23
    為に
    2.06
     Dinas
    1.96
     gewi
    1.94
     quintessential
    1.87
    嫑
    1.84
     REALLY
    1.84
     boister
    1.82
     -'
    1.80
     revamped
    1.78
    Activations Density 0.007%

    No Known Activations