© 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. 201991
    Prev
    Next
    INDEX
    Explanations

    aerodynamic optimi

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

    less meaningful than

    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
     salut
    0.48
    amarca
    0.48
     consultancy
    0.46
     antipode
    0.46
     lions
    0.46
    <0x81>
    0.45
     SIGNIFIC
    0.43
     $'
    0.43
     crumbs
    0.43
     symb
    0.43
    POSITIVE LOGITS
     يمكنك
    0.51
    把
    0.50
    たり
    0.50
    想着
    0.48
     možete
    0.47
    特征
    0.46
    不仅
    0.45
     przesz
    0.45
    时
    0.45
    ра
    0.45
    Activations Density 0.001%

    No Known Activations