© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128254
    Prev
    Next
    INDEX
    Explanations

    mainly, primarily, but

    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
    -1.39
     many
    -1.38
     could
    -1.30
     might
    -1.30
     may
    -1.29
     which
    -1.26
     possibly
    -1.25
     both
    -1.23
     sometimes
    -1.23
     almost
    -1.20
    POSITIVE LOGITS
     but
    1.60
     ولكن
    1.58
     แต่
    1.48
     لكن
    1.29
     nhưng
    1.24
     But
    1.20
     但是
    1.17
     אך
    1.10
    but
    1.07
    BUT
    1.03
    Activations Density 0.154%

    No Known Activations