© 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. 26330
    Prev
    Next
    INDEX
    Explanations

    thani, rouhani, decision, role, you, music

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

    government python apps

    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
    ніка
    0.49
     UpdateWindow
    0.46
    ментів
    0.45
    QWidget
    0.44
    褰
    0.43
     ফিল্ম
    0.43
    ্বর
    0.42
     berlaku
    0.42
    ﻀ
    0.42
    ায়ার
    0.42
    POSITIVE LOGITS
    ✗
    0.48
    de
    0.48
    ats
    0.48
    ey
    0.47
    ius
    0.46
    ni
    0.46
    ew
    0.45
    ec
    0.45
    wins
    0.45
    ipas
    0.45
    Activations Density 0.000%

    No Known Activations