© 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. 19035
    Prev
    Next
    INDEX
    Explanations

    conflict and resolution

    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
    苳
    -2.23
     stabili
    -2.17
    簠
    -2.16
     positioned
    -2.08
    鱟
    -2.06
    ⽤
    -2.05
    IN
    -2.03
    嘥
    -2.02
    餿
    -1.94
    of
    -1.92
    POSITIVE LOGITS
    咘
    2.42
     nieuwe
    2.22
    the
    2.16
    ࿇
    2.13
    țiile
    2.11
     melalui
    2.09
    也将
    2.09
     丁目
    2.08
    \
    2.08
     帅气
    2.06
    Activations Density 0.006%

    No Known Activations