© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70455
    Prev
    Next
    INDEX
    Explanations

    compiler directives or code warnings

    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
     their
    -2.20
     its
    -1.74
    ieR
    -1.38
     decidido
    -1.33
     several
    -1.30
     répon
    -1.30
     his
    -1.28
    鐧
    -1.28
     esponja
    -1.27
    chaise
    -1.27
    POSITIVE LOGITS
    </em>
    1.34
     لأنه
    1.21
     normalen
    1.16
    なので
    1.15
    ici
    1.14
     trad
    1.13
    8
    1.13
     Después
    1.13
     finalement
    1.13
    vantaged
    1.12
    Activations Density 0.001%

    No Known Activations