© 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. 34271
    Prev
    Next
    INDEX
    Explanations

    scientific journal abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite

    academic journal name abbreviations in scientific citations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Vorgang
    -1.37
     também
    -1.34
     alſo
    -1.34
    Также
    -1.32
    danke
    -1.27
     dibuka
    -1.25
     constate
    -1.24
     your
    -1.23
     stili
    -1.23
     situe
    -1.23
    POSITIVE LOGITS
    ,
    1.57
    1.23
     Although
    1.16
    ➩
    1.16
    -
    1.16
     B
    1.12
     as
    1.09
    al
    1.06
    </em>
    1.06
     S
    1.05
    Activations Density 0.007%
    No Known Activations