© 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. 34145
    Prev
    Next
    INDEX
    Explanations

    positive support and appreciation

    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
     only
    -1.16
     but
    -1.15
    ૩
    -1.14
    的过程
    -1.12
     or
    -1.12
     after
    -1.11
    ૪
    -1.09
    incontro
    -1.08
     then
    -1.07
     約
    -1.06
    POSITIVE LOGITS
     help
    1.94
    也很
    1.24
     giúp
    1.23
     support
    1.22
     کمک
    1.20
     assist
    1.18
    |>
    1.16
    help
    1.16
     crucial
    1.16
     Crédit
    1.14
    Activations Density 0.020%

    No Known Activations