© 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. 22-GEMMASCOPE-RES-131K
    7. 14903
    Prev
    Next
    INDEX
    Explanations

    cause or example of

    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
    önt
    -1.21
     suministros
    -1.19
    同樣
    -1.17
     acoged
    -1.17
    を行いました
    -1.16
    Enough
    -1.15
     гораздо
    -1.14
     genauso
    -1.13
     Ответить
    -1.12
    줬
    -1.12
    POSITIVE LOGITS
     of
    4.38
     to
    2.22
     that
    2.03
     in
    1.99
     for
    1.87
     on
    1.80
     any
    1.60
     ever
    1.57
     anyone
    1.51
     you
    1.45
    Activations Density 0.051%

    No Known Activations