© 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. 164619
    Prev
    Next
    INDEX
    Explanations

    location or handler

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

    self-awareness, preservation, Platform Policies

    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
    аб
    0.50
     tyrant
    0.49
    周年
    0.45
    JDK
    0.45
     ailing
    0.45
     tyrannical
    0.45
    傑
    0.44
     divisive
    0.44
     especialistas
    0.43
    განი
    0.43
    POSITIVE LOGITS
    t
    0.53
    setFillColor
    0.51
     گرد
    0.50
     Biss
    0.49
    structed
    0.48
     Scholarship
    0.47
     Oswego
    0.47
     chào
    0.46
    urches
    0.46
     Greetings
    0.46
    Activations Density 0.001%

    No Known Activations