© 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. 12078
    Prev
    Next
    INDEX
    Explanations

    phrases like relates to

    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
     prič
    -1.44
    ՝
    -1.16
    agad
    -1.05
     šte
    -1.04
     blir
    -1.04
     féminine
    -1.02
    ļas
    -1.01
    знать
    -1.01
     suspicions
    -0.99
     vč
    -0.99
    POSITIVE LOGITS
     available
    1.54
    也沒有
    1.27
    有助
    1.23
    ordre
    1.22
     than
    1.18
    שׂ
    1.16
    能夠
    1.16
    </h6>
    1.15
     brune
    1.13
     popolari
    1.13
    Activations Density 0.055%

    No Known Activations