© 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. 165140
    Prev
    Next
    INDEX
    Explanations

    common phrases

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

    used for or followed by purpose

    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
     ሂደ
    0.49
     Ư
    0.49
     দখলে
    0.47
     市場
    0.47
     ఉత్ప
    0.47
     યોગ
    0.46
     আদায়
    0.46
     Интере
    0.46
     polymorphisms
    0.46
     ಹೋ
    0.46
    POSITIVE LOGITS
    ing
    0.53
    v
    0.53
    je
    0.52
    keun
    0.52
     yang
    0.47
    ",
    0.47
    ::
    0.47
    为了
    0.47
    kons
    0.46
     kane
    0.46
    Activations Density 0.001%

    No Known Activations