© 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. 10-GEMMASCOPE-RES-131K
    7. 103998
    Prev
    Next
    INDEX
    Explanations

    introducing exceptional cases

    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
     also
    -2.83
    \
    -2.80
    at
    -2.52
     of
    -2.41
    S
    -2.16
     &
    -2.11
    also
    -2.08
    L
    -1.89
    K
    -1.87
     about
    -1.76
    POSITIVE LOGITS
    卨
    2.20
    旆
    2.09
    ╣
    2.09
    forKey
    2.05
     texturas
    2.03
    ⽉
    2.00
    𖤣
    1.99
     puas
    1.94
    🗹
    1.88
    діа
    1.86
    Activations Density 0.028%

    No Known Activations