© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17326
    Prev
    Next
    INDEX
    Explanations

    version numbers and grades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🐽
    0.42
    🐷
    0.39
     ruj
    0.38
     결혼
    0.36
    🐒
    0.36
    Đây
    0.36
    ◝
    0.35
    🐖
    0.34
     luglio
    0.34
    👆
    0.34
    POSITIVE LOGITS
    ex
    0.39
    ਪ
    0.38
    INV
    0.38
    ეგის
    0.38
    ַ
    0.38
     mời
    0.38
    abilidade
    0.37
     அன்பு
    0.37
     Conference
    0.37
    மெ
    0.37
    Activations Density 0.000%

    No Known Activations