© 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. 74015
    Prev
    Next
    INDEX
    Explanations

    missing about, having in mind

    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
     this
    -1.63
     their
    -1.49
     acestei
    -1.20
     acestui
    -1.11
     these
    -1.11
     our
    -1.06
    וּ
    -1.05
    ならば
    -1.01
    resiasi
    -1.01
     terbaru
    -0.98
    POSITIVE LOGITS
     časti
    1.32
     experience
    1.30
     člán
    1.21
    waits
    1.21
     experiences
    1.21
    🧌
    1.19
     ENJOY
    1.19
     enjoyment
    1.16
    enjoy
    1.16
    asztal
    1.15
    Activations Density 0.045%

    No Known Activations