© 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. 34-GEMMASCOPE-RES-131K
    4. 115974
    Prev
    Next
    INDEX
    Explanations

    Telegram channel or bot

    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
    emails
    -0.86
     Facebook
    -0.81
    Emails
    -0.80
    ByEmail
    -0.79
    Facebook
    -0.75
    жную
    -0.75
    常
    -0.74
     febbraio
    -0.73
     emails
    -0.72
     altezza
    -0.71
    POSITIVE LOGITS
     channel
    1.10
    Channel
    1.02
     CHANNEL
    1.00
    channel
    0.98
     Channel
    0.98
     tg
    0.98
     Bot
    0.94
    Channels
    0.92
    Tg
    0.90
     channels
    0.89
    Activations Density 0.012%

    No Known Activations