© 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. 83755
    Prev
    Next
    INDEX
    Explanations

    month where, miss this, conclusive acceptance

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

    crucial social event

    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
    and
    0.54
     %.
    0.51
    %.
    0.50
    ni
    0.49
    pp
    0.49
     and
    0.48
    ttier
    0.48
    et
    0.47
     but
    0.47
    hide
    0.47
    POSITIVE LOGITS
    姮
    0.55
     التاريخ
    0.51
    秫
    0.51
    箜
    0.51
     Seorang
    0.50
    芫
    0.50
     Ön
    0.49
     непоня
    0.49
     талант
    0.48
    룺
    0.48
    Activations Density 0.001%

    No Known Activations