© 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. 10-GEMMASCOPE-RES-131K
    4. 130619
    Prev
    Next
    INDEX
    Explanations

    observation and action verbs

    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_10/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
     you
    -1.63
     nyní
    -1.45
    </sup>
    -1.45
     maceta
    -1.38
     budete
    -1.37
     теперь
    -1.37
    ociação
    -1.35
    cheibe
    -1.32
     will
    -1.32
     można
    -1.31
    POSITIVE LOGITS
     to
    1.29
    at
    1.26
    If
    1.25
    抨
    1.20
     on
    1.15
    ,
    1.13
     overall
    1.13
     orchestr
    1.12
    請繼續往下閱讀
    1.10
    bok
    1.09
    Activations Density 0.024%

    No Known Activations