© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184246
    Prev
    Next
    INDEX
    Explanations

    verb completions

    np_acts-logits-general · gemini-2.5-flash-lite

    combination of elements or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     installer
    0.48
     pharma
    0.47
     advertisers
    0.46
     pharmaceutical
    0.46
     i
    0.46
     lockers
    0.46
     is
    0.45
     installed
    0.45
     pharmacy
    0.45
     parking
    0.45
    POSITIVE LOGITS
    დან
    0.53
    י
    0.51
    вили
    0.50
    チーズ
    0.48
    집
    0.48
    ޒ
    0.47
    ⵣ
    0.46
    Collections
    0.45
    アウト
    0.45
    ت
    0.45
    Activations Density 0.002%

    No Known Activations