© 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. 105891
    Prev
    Next
    INDEX
    Explanations

    rights, fame, maximization

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

    rules or game instructions

    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
     whose
    0.50
    ํ
    0.50
     bears
    0.50
     assaulted
    0.48
     around
    0.47
     trenches
    0.47
     partners
    0.47
     compatriots
    0.47
    菁
    0.47
     constituted
    0.46
    POSITIVE LOGITS
    Ộ
    0.54
    Setpoint
    0.50
     приро
    0.47
    
    0.47
    ichtigung
    0.46
    iliği
    0.46
     вода
    0.45
     μαγγ
    0.45
    ště
    0.45
     воду
    0.45
    Activations Density 0.001%

    No Known Activations