© 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. 15011
    Prev
    Next
    INDEX
    Explanations

    text in quotes followed by category or tag

    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
     sué
    -1.33
     是
    -1.27
     feminina
    -1.23
     seront
    -1.23
     ideen
    -1.16
     včetně
    -1.16
     consulte
    -1.15
     casada
    -1.15
     lança
    -1.15
     “
    -1.14
    POSITIVE LOGITS
     we
    1.64
     at
    1.29
     никогда
    1.23
    竅
    1.18
    ult
    1.12
    訊息
    1.11
     håll
    1.11
     '+'
    1.10
    えません
    1.10
    俱乐
    1.06
    Activations Density 0.005%

    No Known Activations