© 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. 69080
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases and clauses

    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
    zwischen
    -1.35
     klar
    -1.34
     Rakyat
    -1.29
     roja
    -1.27
            
    -1.27
     THOSE
    -1.23
    、
    -1.22
    those
    -1.20
     иметь
    -1.20
     celles
    -1.20
    POSITIVE LOGITS
     like
    1.60
     only
    1.54
     relentlessly
    1.37
     already
    1.31
    んびり
    1.28
     before
    1.27
     subida
    1.26
     mentally
    1.23
     until
    1.22
    地说
    1.22
    Activations Density 0.153%

    No Known Activations