© 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. 15841
    Prev
    Next
    INDEX
    Explanations

    phrases introducing examples or explanations

    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
    R
    -1.34
    L
    -1.32
    H
    -1.26
    M
    -1.22
    C
    -1.21
    Y
    -1.21
    V
    -1.16
    F
    -1.13
    olge
    -1.13
    D
    -1.13
    POSITIVE LOGITS
    Contoh
    1.51
    Fungsi
    1.34
    Masukkan
    1.29
     kabát
    1.20
    Ukuran
    1.17
    JAJA
    1.16
    Terima
    1.16
    Penjelasan
    1.15
    importation
    1.14
    Ingrédients
    1.13
    Activations Density 0.002%

    No Known Activations