© 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. 23885
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by auxiliaries or common verbs

    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
     ifølge
    -1.45
    ichtet
    -1.45
     to
    -1.43
    NÍ
    -1.43
     karena
    -1.41
    uruh
    -1.40
    ourites
    -1.39
     on
    -1.38
    .*;
    -1.34
    туру
    -1.33
    POSITIVE LOGITS
     its
    1.79
     know
    1.68
    它是
    1.59
    了嗎
    1.59
     nasze
    1.54
     also
    1.45
     mogę
    1.39
     zobac
    1.39
    its
    1.38
    졌
    1.36
    Activations Density 0.094%

    No Known Activations