© 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. 104664
    Prev
    Next
    INDEX
    Explanations

    urls with slash

    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
    -1.44
     this
    -1.25
    ∅
    -1.23
     från
    -1.20
    線の
    -1.20
    OrNil
    -1.20
    ).
    -1.17
     can
    -1.17
    ),
    -1.16
     in
    -1.15
    POSITIVE LOGITS
     jezt
    1.33
     decisivo
    1.27
    nowe
    1.22
     figliu
    1.21
    Эзоҳ
    1.20
    dentro
    1.19
     SHOWS
    1.17
    깻
    1.17
    espero
    1.16
     weihnachten
    1.16
    Activations Density 0.007%

    No Known Activations