© 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. 34-GEMMASCOPE-RES-131K
    7. 4115
    Prev
    Next
    INDEX
    Explanations

    words before articles or determiners

    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_34/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
     it
    -1.44
     this
    -1.34
     its
    -1.26
     their
    -1.20
     a
    -1.19
     these
    -1.17
     our
    -1.06
     that
    -0.98
     BoxFit
    -0.93
     Ma
    -0.92
    POSITIVE LOGITS
     the
    4.28
     той
    1.33
     जिस
    1.32
     যে
    1.16
     những
    1.16
    掺
    1.02
     olyan
    0.99
     nasional
    0.98
     тот
    0.96
    ateľ
    0.95
    Activations Density 0.167%

    No Known Activations