© 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. 12014
    Prev
    Next
    INDEX
    Explanations

    you were / it is

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

    pronoun + verb/auxiliary

    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
    を有する
    0.37
     einschließlich
    0.37
    Რ
    0.36
     acknowledgment
    0.35
     newApproved
    0.35
    ุม
    0.34
    持つ
    0.34
    ূন্য
    0.33
     outperforms
    0.33
     végétation
    0.33
    POSITIVE LOGITS
     de
    0.41
     can
    0.38
    d
    0.38
     really
    0.35
    )
    0.35
    ﾃ
    0.35
    upe
    0.34
    ottie
    0.33
     T
    0.32
     Exchequer
    0.32
    Activations Density 0.488%

    No Known Activations