© 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. 96137
    Prev
    Next
    INDEX
    Explanations

    purpose of alternative methods

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

    potential energy leaks

    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
     handkerchief
    0.49
    kerchief
    0.48
    াল্ড
    0.46
    rova
    0.46
    ktops
    0.46
    LOLLIPOP
    0.45
     দিবার
    0.45
     ，
    0.45
     robes
    0.44
     shawl
    0.44
    POSITIVE LOGITS
    𝔀
    0.52
     교
    0.50
    িত্তিক
    0.49
    ωση
    0.48
     mục
    0.47
    이션
    0.47
     γε
    0.46
    性と
    0.46
    ни
    0.46
    ι
    0.46
    Activations Density 0.000%

    No Known Activations