© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33174
    Prev
    Next
    INDEX
    Explanations

    LayoutInflater and view inflation

    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
     on
    -1.52
     will
    -1.43
     With
    -1.41
     in
    -1.37
    There
    -1.34
    悌
    -1.29
    With
    -1.29
     when
    -1.23
     all
    -1.23
    When
    -1.19
    POSITIVE LOGITS
    拊
    1.24
     délais
    1.20
     ſub
    1.17
    垟
    1.16
     maniere
    1.16
    埝
    1.15
     échanti
    1.15
     sentier
    1.14
     vaisseaux
    1.13
     pétrole
    1.13
    Activations Density 0.001%

    No Known Activations