© 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. 124834
    Prev
    Next
    INDEX
    Explanations

    Goldman Sachs banks

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

    guest, walking, eclipse, ecosystem, systemic, conjugation

    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
    𝚄
    0.54
    😗
    0.51
     bude
    0.50
    異なる
    0.50
     কিছুদিন
    0.48
    ಿಯೂ
    0.48
    िखर
    0.47
    アップ
    0.46
    ビー
    0.46
     различни
    0.46
    POSITIVE LOGITS
    ج
    0.43
    àng
    0.42
     memor
    0.41
    лт
    0.40
     Españ
    0.40
    HDL
    0.39
    intas
    0.39
    ösen
    0.39
     imm
    0.38
     enum
    0.38
    Activations Density 0.000%

    No Known Activations