© 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. 202348
    Prev
    Next
    INDEX
    Explanations

    persistently manage, was coming from, have wanted

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

    crucially important first step

    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
     receta
    0.50
    QtCore
    0.48
     banned
    0.47
    ﻳ
    0.47
    ierta
    0.47
    ﺔ
    0.47
     as
    0.46
    ClrType
    0.46
    ="$(
    0.45
     magia
    0.45
    POSITIVE LOGITS
     डेफ
    0.49
    ostic
    0.49
     Petit
    0.48
     Relatively
    0.47
    uh
    0.46
    ujem
    0.46
     مرکزی
    0.46
    resto
    0.46
     Orchard
    0.44
    manip
    0.44
    Activations Density 0.000%

    No Known Activations