© 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. 27628
    Prev
    Next
    INDEX
    Explanations

    to improvement actions

    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
     rekke
    -1.46
     række
    -1.36
     observaciones
    -1.34
    butuhkan
    -1.34
     razões
    -1.32
    Typically
    -1.31
    During
    -1.30
    Bisous
    -1.30
     bosques
    -1.30
    When
    -1.29
    POSITIVE LOGITS
     better
    1.42
     السياس
    1.27
     ensure
    1.23
     future
    1.23
     лучше
    1.21
    :
    1.20
     we
    1.20
     our
    1.17
     الحكومة
    1.17
     rheinland
    1.15
    Activations Density 0.049%

    No Known Activations