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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17901
    Prev
    Next
    INDEX
    Explanations

    community and ethics

    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
     Dubai
    0.46
    Romeo
    0.44
    ჩ
    0.44
    ires
    0.43
     stadiums
    0.43
    Dubai
    0.43
     Riyadh
    0.42
     milligrams
    0.42
    ἱ
    0.42
    ▓
    0.41
    POSITIVE LOGITS
     anarchist
    0.99
     anarch
    0.92
     community
    0.80
    Community
    0.78
     Community
    0.75
     koperasi
    0.73
    community
    0.72
     pacif
    0.72
     decentral
    0.71
     communautés
    0.71
    Activations Density 0.163%

    No Known Activations