© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13171
    Prev
    Next
    INDEX
    Explanations

    create, add, install, enable, modify

    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
    idk
    -1.13
    ふわ
    -1.07
    VISIT
    -1.06
    IDK
    -1.06
    hmmm
    -1.04
    provides
    -1.02
     prouver
    -1.01
     constate
    -1.01
    primarily
    -1.01
    providing
    -1.00
    POSITIVE LOGITS
     new
    2.05
     one
    1.41
     including
    1.37
     as
    1.34
     by
    1.20
     started
    1.18
     tries
    1.13
     expertly
    1.11
     or
    1.10
     first
    1.10
    Activations Density 0.004%

    No Known Activations