© 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. 95712
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    chengladbach
    -1.11
    ヵ
    -1.07
     olika
    -1.07
    
    -1.02
    issä
    -1.02
     venant
    -1.00
     gynnwys
    -1.00
    dáms
    -1.00
    liputi
    -0.99
     verschiedenen
    -0.98
    POSITIVE LOGITS
     a
    1.55
     an
    1.20
     something
    1.06
     both
    1.02
    hasOwnProperty
    1.00
     most
    0.97
    صالات
    0.96
    詳しくは
    0.90
     more
    0.90
     several
    0.88
    Activations Density 0.008%

    No Known Activations