© 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. 35768
    Prev
    Next
    INDEX
    Explanations

    each particle, tuple, star

    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
    ㌧
    -1.44
     suscit
    -1.39
    💢
    -1.38
    brille
    -1.34
    Cierre
    -1.32
    ᡴ
    -1.32
     magnum
    -1.31
    bringing
    -1.31
    伥
    -1.31
    fought
    -1.30
    POSITIVE LOGITS
     each
    1.63
    1.51
     erinnern
    1.33
     data
    1.32
     things
    1.29
     items
    1.25
     children
    1.24
     particular
    1.21
     payment
    1.21
     afectadas
    1.20
    Activations Density 0.370%

    No Known Activations