© 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. 130836
    Prev
    Next
    INDEX
    Explanations

    casting, role, talks, involvement

    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
     السياس
    -1.48
    𝒙
    -1.21
    $\%$
    -1.08
     criptomonedas
    -1.05
    companied
    -1.05
    って感じ
    -1.05
    DELIM
    -1.04
    ksesta
    -1.04
     goals
    -1.03
     तरी
    -1.03
    POSITIVE LOGITS
    genöss
    1.23
     projektu
    1.22
     verhind
    1.20
    mainAxisSize
    1.19
    楽しめます
    1.19
     LINE
    1.18
     acheter
    1.15
     nadru
    1.15
     osoby
    1.14
     eventuali
    1.14
    Activations Density 0.013%

    No Known Activations