© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 112166
    Prev
    Next
    INDEX
    Explanations

    international employee benefits

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

    **Allow for mistakes:

    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
     hải
    0.58
     vẽ
    0.55
    CONNECTION
    0.55
     biển
    0.55
     xảy
    0.54
    ="..\
    0.53
    ෙන්
    0.51
     kẻ
    0.51
    FRAGMENT
    0.50
     ServicePolicy
    0.50
    POSITIVE LOGITS
     I
    0.46
     breath
    0.46
     mirror
    0.46
    breath
    0.45
     driver
    0.45
     DMP
    0.44
    D
    0.44
     visitor
    0.43
    al
    0.43
    ent
    0.43
    Activations Density 0.000%

    No Known Activations