© 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. 189948
    Prev
    Next
    INDEX
    Explanations

    fee, us, held, events, lock, short

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

    consequence, medication, hardware, firms

    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
     manage
    0.45
     divis
    0.43
     bargain
    0.42
     dépassant
    0.41
     demonstrate
    0.40
     promote
    0.39
     Crafted
    0.39
    规
    0.39
    报
    0.39
     execute
    0.39
    POSITIVE LOGITS
     وہاں
    0.52
    THERE
    0.50
     ところ
    0.49
     araç
    0.49
     위에
    0.47
    ిక
    0.46
     সেখানে
    0.46
     അവിടെ
    0.46
    (\{
    0.46
    
    0.46
    Activations Density 0.001%

    No Known Activations