© 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. 28374
    Prev
    Next
    INDEX
    Explanations

    Sebastian Siebrecht

    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
    ছে
    -1.12
     emplois
    -1.11
    Exited
    -1.08
    ärin
    -1.02
     cúp
    -1.01
     <",
    -1.00
     localização
    -1.00
    ⚣
    -1.00
     ilustração
    -1.00
     they
    -0.99
    POSITIVE LOGITS
     another
    1.22
     from
    1.08
    ਿੰ
    1.01
     voidaan
    0.95
     at
    0.90
     fourth
    0.89
     any
    0.88
     sixth
    0.88
     trier
    0.85
     trataba
    0.85
    Activations Density 0.000%

    No Known Activations