© 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. 65779
    Prev
    Next
    INDEX
    Explanations

    Mr. followed by name

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

    understand nuance and context

    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
    께서
    0.43
     высота
    0.42
    pliance
    0.41
    ScreenBinding
    0.41
     спасибо
    0.41
    ዃ
    0.41
     supposing
    0.39
    EDA
    0.39
    🤍
    0.39
    enediamine
    0.38
    POSITIVE LOGITS
    بی
    0.43
    ველ
    0.43
    และการ
    0.42
    styr
    0.42
     এবং
    0.41
     _{
    0.40
     Kont
    0.40
    payroll
    0.40
    诨
    0.40
     east
    0.40
    Activations Density 0.001%

    No Known Activations