© 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. 174400
    Prev
    Next
    INDEX
    Explanations

    owned materials, one words, partner prize

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

    Quantum, Register, Indicator, Trop, case

    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
    um
    0.50
    此
    0.48
    Wei
    0.48
    Be
    0.47
    Wood
    0.47
    Пред
    0.47
    “
    0.46
    Son
    0.46
    ຈ
    0.46
    Бе
    0.45
    POSITIVE LOGITS
    琙
    0.54
    ையில்
    0.52
    েন্টের
    0.50
     wpływ
    0.45
     maintien
    0.45
     dobry
    0.44
     ;\
    0.43
    лям
    0.43
     miesz
    0.42
     timescales
    0.42
    Activations Density 0.000%

    No Known Activations