© 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. 34-GEMMASCOPE-RES-131K
    7. 49616
    Prev
    Next
    INDEX
    Explanations

    Another followed by a noun

    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_34/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
    voer
    -1.25
    Вита
    -1.17
    chery
    -1.16
    formazioni
    -1.14
    mô
    -1.13
     bè
    -1.12
    signia
    -1.09
    ѧ
    -1.09
     vilja
    -1.06
    bės
    -1.05
    POSITIVE LOGITS
     is
    2.22
     important
    2.20
     factor
    1.72
     thing
    1.72
     notable
    1.67
     major
    1.60
     aspect
    1.57
    ,
    1.52
     way
    1.48
     obvious
    1.47
    Activations Density 0.041%

    No Known Activations