© 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. 110966
    Prev
    Next
    INDEX
    Explanations

    status or employee or piece

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

    describing castles and children

    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
     expands
    0.48
     anew
    0.47
     Galleria
    0.46
    画像
    0.45
     ORDERS
    0.43
    ゚
    0.42
     “‘
    0.41
    ִ
    0.41
     kä
    0.41
     tượng
    0.41
    POSITIVE LOGITS
     nonstop
    0.47
    erit
    0.47
     ড্রাই
    0.47
    一下子
    0.47
    ehir
    0.46
     convid
    0.45
     desemb
    0.44
     compagnies
    0.44
     плану
    0.44
    끊
    0.44
    Activations Density 0.000%

    No Known Activations