© 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. 27911
    Prev
    Next
    INDEX
    Explanations

    programming template and comments

    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
     katalog
    -1.14
     Etik
    -1.10
     his
    -1.03
     flott
    -1.03
     konfer
    -1.02
     工事
    -1.02
    paket
    -1.00
     Ráp
    -1.00
    beton
    -1.00
     gitar
    -1.00
    POSITIVE LOGITS
     during
    1.21
     this
    1.16
    sistors
    1.02
     незавер
    0.99
     según
    0.99
    quirer
    0.97
    ớp
    0.96
     implemented
    0.96
    this
    0.96
    ()?;
    0.95
    Activations Density 0.003%

    No Known Activations