© 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. 161563
    Prev
    Next
    INDEX
    Explanations

    marketing efforts

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

    bright vs dark

    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
    SUPER
    0.52
    ِيم
    0.50
    FUND
    0.49
     romanzo
    0.49
    GROW
    0.49
    িব
    0.48
    علي
    0.48
    ﻌ
    0.48
     sağlam
    0.48
    َع
    0.47
    POSITIVE LOGITS
    lt
    0.49
    awn
    0.49
    ointing
    0.49
    nia
    0.47
    ion
    0.47
    ank
    0.47
    ds
    0.47
    agle
    0.46
    dm
    0.46
    lor
    0.46
    Activations Density 0.001%

    No Known Activations