© 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. 54115
    Prev
    Next
    INDEX
    Explanations

    electronic components

    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
     absurdo
    -1.17
     categorias
    -1.12
     hysterical
    -1.07
    ctia
    -1.05
     srdce
    -1.05
    あー
    -1.01
    blia
    -0.99
    ésor
    -0.98
    parian
    -0.97
     توانید
    -0.96
    POSITIVE LOGITS
     not
    1.20
     then
    1.16
    ($)
    1.03
     DWORD
    1.02
    栞
    0.98
     how
    0.98
     normally
    0.91
    then
    0.91
    borderSide
    0.90
     because
    0.89
    Activations Density 0.210%

    No Known Activations