© 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. 192036
    Prev
    Next
    INDEX
    Explanations

    sessions, they, throughout, respect, experience

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

    let's build a book outline

    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
    Seen
    0.45
    אי
    0.44
    명의
    0.42
    硏
    0.42
    Watts
    0.39
    \{
    0.39
    Cand
    0.39
    경제
    0.39
     বেশী
    0.38
    Most
    0.38
    POSITIVE LOGITS
     माझ्या
    0.51
     Workbook
    0.48
     अभिकथन
    0.47
     Autobi
    0.47
     Mittag
    0.47
    ᵚ
    0.46
     Mulligan
    0.46
    tiger
    0.46
     Resize
    0.46
     TabLayout
    0.46
    Activations Density 0.001%

    No Known Activations