© 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. 10-GEMMASCOPE-RES-131K
    7. 111411
    Prev
    Next
    INDEX
    Explanations

    names and initials

    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_10/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
     История
    -1.37
    媄
    -1.27
     bisous
    -1.18
     vode
    -1.16
    ificazione
    -1.16
     ihe
    -1.15
    ۱۵
    -1.14
     ciento
    -1.14
    delà
    -1.13
    viembre
    -1.13
    POSITIVE LOGITS
     had
    1.48
     '
    1.48
     in
    1.37
    ,"\
    1.30
     "
    1.29
     didn
    1.27
    had
    1.17
    -"
    1.17
    でも
    1.16
    dalen
    1.16
    Activations Density 0.055%

    No Known Activations