© 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. 10-GEMMASCOPE-RES-131K
    7. 1619
    Prev
    Next
    INDEX
    Explanations

    code identifiers and values

    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_10/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
     has
    -2.75
     after
    -2.59
     this
    -2.58
     for
    -2.52
     with
    -2.47
     during
    -2.34
     During
    -2.30
     new
    -2.16
     When
    -2.14
     becomes
    -2.14
    POSITIVE LOGITS
    袛
    2.19
     eſſ
    2.17
    ཥ
    2.09
     geene
    2.09
     siè
    2.09
    歺
    2.08
     italiens
    2.06
     magasins
    2.05
    のもの
    2.03
     unſ
    2.00
    Activations Density 0.050%

    No Known Activations