© 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. 34-GEMMASCOPE-RES-131K
    7. 116538
    Prev
    Next
    INDEX
    Explanations

    protocol entities, messages, transfer

    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_34/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
    вайтесь
    -0.76
     TextStyle
    -0.68
     digno
    -0.68
    察
    -0.67
     Fern
    -0.67
    ^{-}$
    -0.67
    影视
    -0.66
    veri
    -0.66
     připo
    -0.64
     psico
    -0.63
    POSITIVE LOGITS
     message
    4.41
     messages
    4.31
    message
    3.56
    messages
    3.27
     Messages
    3.22
    Message
    3.13
     msg
    3.11
     Message
    3.09
    msg
    3.02
    Messages
    2.84
    Activations Density 0.113%

    No Known Activations