© 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. 9796
    Prev
    Next
    INDEX
    Explanations

    hope for, thrombosis presented, icon on

    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
    aceite
    -1.39
     erhi
    -1.37
    espero
    -1.28
    色々と
    -1.27
    alimentos
    -1.24
    símbolo
    -1.23
     feltro
    -1.23
    に到着
    -1.21
     célè
    -1.20
    很赞
    -1.20
    POSITIVE LOGITS
     to
    1.15
     by
    1.09
    內容簡介
    1.07
    randi
    1.02
     in
    1.02
     of
    1.01
     from
    1.00
     with
    1.00
    queryInterface
    0.99
    ;
    0.98
    Activations Density 0.052%

    No Known Activations