© 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. 68776
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
    ionali
    -1.05
    нии
    -1.03
     если
    -1.02
    daki
    -1.01
    новь
    -0.99
    ;
    -0.99
     menghapus
    -0.98
    €“
    -0.98
    Printf
    -0.97
    bės
    -0.97
    POSITIVE LOGITS
     himself
    1.41
     therefore
    1.26
    tiac
    1.14
    ricing
    1.13
     thus
    1.11
    ないけど
    1.06
     сам
    1.05
     别墅
    1.05
     thereby
    1.04
     チェック
    1.04
    Activations Density 0.090%

    No Known Activations