© 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. 10870
    Prev
    Next
    INDEX
    Explanations

    compound word beginnings

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

    demon, Jurassic, chemical, privilege, magic, regret

    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
     GoObject
    0.39
     Sf
    0.38
    javafx
    0.38
    ্বরূপ
    0.37
    hookrightarrow
    0.36
    】,
    0.36
    ൦
    0.36
    '];
    0.36
    src
    0.35
    drawable
    0.35
    POSITIVE LOGITS
     totalitarian
    0.53
     bureaucrats
    0.52
     pundits
    0.51
     asshole
    0.51
     wunder
    0.50
     raconte
    0.50
    统治
    0.48
     badass
    0.47
     visage
    0.47
     douche
    0.47
    Activations Density 0.123%

    No Known Activations