© 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. 68077
    Prev
    Next
    INDEX
    Explanations

    roman numerals and numbers in legal contexts

    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
    様々
    -1.26
     various
    -1.24
     ebenso
    -1.19
    豊富な
    -1.12
     traditional
    -1.09
     vermutlich
    -1.09
     also
    -1.09
     start
    -1.07
     wahrscheinlich
    -1.05
     allein
    -1.04
    POSITIVE LOGITS
     jú
    1.52
    และ
    1.46
     flotte
    1.33
     délicieux
    1.32
     fré
    1.31
    giày
    1.30
    ContentAlignment
    1.30
    놋
    1.30
     RÉ
    1.28
     fidé
    1.27
    Activations Density 0.090%

    No Known Activations