© 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. 10-GEMMASCOPE-RES-131K
    4. 90862
    Prev
    Next
    INDEX
    Explanations

    attention, warnings, and bugs

    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_10/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
    ximate
    -1.40
    ᮣ
    -1.37
     ‘‘
    -1.34
    GINIA
    -1.30
    odorant
    -1.27
     suficientes
    -1.27
    accines
    -1.27
     same
    -1.26
     like
    -1.26
    ută
    -1.24
    POSITIVE LOGITS
    ↵
    1.43
    !'
    1.33
    !')
    1.28
    '
    1.25
    一起
    1.24
    ..."
    1.20
    每天
    1.19
     alfo
    1.19
    Fig
    1.19
    ?"
    1.19
    Activations Density 0.011%

    No Known Activations