© 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. 98129
    Prev
    Next
    INDEX
    Explanations

    Nigerian Content Seminar

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

    program-like structures and specific events

    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
     system
    0.46
     portrayal
    0.46
     meek
    0.45
     entryway
    0.44
     System
    0.43
     autophagy
    0.43
    g
    0.42
     $.
    0.42
     entanglement
    0.42
     (
    0.41
    POSITIVE LOGITS
    いて
    0.55
    годні
    0.54
    iftoire
    0.54
    릿
    0.52
    私は
    0.50
     высоко
    0.50
    лайте
    0.49
    以下の
    0.48
    んですよね
    0.47
     здоров
    0.47
    Activations Density 0.000%

    No Known Activations