© 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. 65170
    Prev
    Next
    INDEX
    Explanations

    verb followed by complement

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

    international words

    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
     imate
    0.45
    οντας
    0.44
    ваете
    0.44
     Colorado
    0.44
    이자
    0.44
    닥
    0.43
     газа
    0.43
     lagu
    0.43
     gemeente
    0.42
     cận
    0.42
    POSITIVE LOGITS
     Eintritt
    0.47
    fetchall
    0.47
     التس
    0.46
     чел
    0.45
     津
    0.45
     ٹک
    0.44
    inner
    0.44
     пай
    0.44
    ӳ
    0.43
    Pais
    0.43
    Activations Density 0.000%

    No Known Activations