© 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. 4675
    Prev
    Next
    INDEX
    Explanations

    if any

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

    cannot and will not

    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
    力和
    0.41
    及び
    0.37
    และ
    0.37
    ۴
    0.36
     आणि
    0.36
    ۵
    0.35
    It
    0.35
    及
    0.34
     및
    0.34
    และการ
    0.34
    POSITIVE LOGITS
     (!)
    0.37
    am
    0.35
    s
    0.35
    en
    0.33
    er
    0.32
     is
    0.32
     таки
    0.32
     당연
    0.32
    ,
    0.32
     является
    0.32
    Activations Density 0.673%

    No Known Activations