© 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. 22-GEMMASCOPE-RES-131K
    7. 27973
    Prev
    Next
    INDEX
    Explanations

    pronouns and conjunctions

    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_22/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
     також
    -1.48
    кож
    -1.48
    恥ず
    -1.38
     citazioni
    -1.38
    也非常
    -1.34
     egyéb
    -1.29
     также
    -1.29
    Also
    -1.27
    悲しい
    -1.26
    こんな感じで
    -1.24
    POSITIVE LOGITS
    而
    1.40
     maybe
    1.30
    MathML
    1.23
    去
    1.18
    或许
    1.15
     roślin
    1.13
     τῶν
    1.13
     شاید
    1.13
     deler
    1.08
     mesmas
    1.08
    Activations Density 0.042%

    No Known Activations