© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 148
    Prev
    Next
    INDEX
    Explanations

    If

    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
     then
    -1.20
     these
    -1.05
     also
    -1.00
     and
    -0.98
     también
    -0.97
     тоже
    -0.93
    …..
    -0.93
    верное
    -0.93
     également
    -0.90
     myös
    -0.88
    POSITIVE LOGITS
     bowiem
    1.34
    //!
    1.24
     literally
    1.20
     cioè
    1.20
     infatti
    1.16
     totiž
    1.13
     lari
    1.11
    kipun
    1.05
    literally
    1.05
    Literally
    1.03
    Activations Density 0.075%

    No Known Activations