© 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. 104509
    Prev
    Next
    INDEX
    Explanations

    sending and receiving messages

    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
     of
    -1.01
    toko
    -0.94
     жили
    -0.94
    DSP
    -0.93
    哪里
    -0.91
    ∷
    -0.90
     взе
    -0.90
    𝐈
    -0.88
    crash
    -0.87
    emails
    -0.87
    POSITIVE LOGITS
     publicar
    1.45
     message
    1.17
     sent
    1.15
     Bewußt
    1.11
     send
    1.09
     conversation
    1.04
     sending
    1.03
     bandoulière
    1.02
     sends
    1.02
    aterdag
    1.02
    Activations Density 0.034%

    No Known Activations