© 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. 246158
    Prev
    Next
    INDEX
    Explanations

    place them

    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
    や
    0.54
    今年も
    0.53
    และ
    0.46
    और
    0.46
    /
    0.46
    ਜ
    0.45
     ή
    0.45
     ওয়ালপেপার
    0.44
    .).
    0.44
    及び
    0.43
    POSITIVE LOGITS
     assailant
    0.53
     turtleneck
    0.45
     inheritance
    0.44
    兕
    0.44
    দোষ
    0.43
     Inheritance
    0.43
     inherited
    0.42
    皙
    0.42
     diphtheria
    0.40
     szület
    0.40
    Activations Density 0.002%

    No Known Activations