© 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. 26127
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    Ông
    -1.57
    我們
    -1.55
    我们
    -1.55
    Alright
    -1.45
     আম
    -1.43
    unduh
    -1.42
     herhangi
    -1.40
     surpren
    -1.40
     аллер
    -1.38
    ТИ
    -1.37
    POSITIVE LOGITS
     like
    1.32
     many
    1.31
     including
    1.30
     sometimes
    1.24
     with
    1.22
     in
    1.22
     together
    1.17
     dozens
    1.16
    istered
    1.14
     those
    1.13
    Activations Density 0.682%

    No Known Activations