© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21116
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -ed or -ing

    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
     mantenga
    -1.72
     it
    -1.58
     imprescin
    -1.55
     impedir
    -1.52
     of
    -1.52
     menyadari
    -1.48
     专业
    -1.45
     about
    -1.45
    by
    -1.43
     tevreden
    -1.42
    POSITIVE LOGITS
    lichkeiten
    1.72
    </em>
    1.63
     Cbd
    1.61
     '*':
    1.59
    fxml
    1.56
     and
    1.54
    hitheatre
    1.53
    achting
    1.52
    zné
    1.52
     recém
    1.48
    Activations Density 0.367%

    No Known Activations