© 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. 15966
    Prev
    Next
    INDEX
    Explanations

    writing, fiction, author, developer

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

    variable declaration and initialization

    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
     QSOs
    0.43
    ülete
    0.43
    CTk
    0.41
     ZOOM
    0.41
    ᄎ
    0.40
    CRR
    0.40
     rollerskates
    0.38
     equilibr
    0.38
     nirv
    0.38
    ๎
    0.38
    POSITIVE LOGITS
    director
    0.39
    这
    0.38
    if
    0.38
    home
    0.38
    只有一个
    0.37
    வர்களுக்கு
    0.37
    parseInt
    0.37
    author
    0.36
     হু
    0.36
     나는
    0.36
    Activations Density 0.028%

    No Known Activations