© 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. 99797
    Prev
    Next
    INDEX
    Explanations

    lattice accent

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

    modular architecture

    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
    ，
    0.46
     eyes
    0.43
     edific
    0.43
     flips
    0.43
     mesa
    0.42
    lor
    0.42
     inser
    0.42
     oatmeal
    0.42
     dân
    0.42
     payoffs
    0.41
    POSITIVE LOGITS
    ริ่ม
    0.54
    attaa
    0.51
    
    0.50
    ริ
    0.46
     سوریه
    0.45
    謖
    0.45
    uparrow
    0.45
    ั
    0.45
    ᐋ
    0.45
    داً
    0.45
    Activations Density 0.000%

    No Known Activations