© 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. 25822
    Prev
    Next
    INDEX
    Explanations

    another/other + 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_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
     and
    -1.26
    を変える
    -1.21
     rispet
    -1.11
     primeiros
    -1.09
     alebo
    -1.09
     ontvang
    -1.02
     сначала
    -1.02
    だけではなく
    -1.01
    有一定
    -1.00
     amélior
    -0.99
    POSITIVE LOGITS
     also
    1.64
     is
    1.59
     other
    1.49
     include
    1.41
     autre
    1.30
     includes
    1.21
     similarly
    1.13
    則是
    1.12
     других
    1.10
     richesse
    1.09
    Activations Density 0.054%

    No Known Activations