© 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. 27651
    Prev
    Next
    INDEX
    Explanations

    in followed by quantifiers

    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
     It
    -1.40
    咄
    -1.30
    ctions
    -1.25
    atchi
    -1.21
     which
    -1.21
    mdash
    -1.21
    us
    -1.20
    日発売
    -1.20
    过头
    -1.18
     utilizando
    -1.17
    POSITIVE LOGITS
     our
    1.56
    Czym
    1.52
     모든
    1.48
    㗎
    1.45
     other
    1.41
    𨧀
    1.41
     both
    1.40
     всички
    1.38
    Wymiary
    1.38
    🗯
    1.37
    Activations Density 0.121%

    No Known Activations