© 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. 20231
    Prev
    Next
    INDEX
    Explanations

    how to phrases and common word pairings

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

    verb followed by preposition/noun

    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
    腰
    0.50
     trif
    0.49
     Infiniti
    0.47
     Percy
    0.46
     رضا
    0.46
     Bern
    0.46
     Innov
    0.45
     highs
    0.45
    ↵
    0.45
     minori
    0.45
    POSITIVE LOGITS
    تعليم
    0.52
    umma
    0.47
     ആശ
    0.45
    umā
    0.45
    oad
    0.45
    ❹
    0.45
    slidesPer
    0.44
    𝗵
    0.44
    openList
    0.44
    ობა
    0.44
    Activations Density 0.000%

    No Known Activations