© 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. 57160
    Prev
    Next
    INDEX
    Explanations

    words including specific entities

    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
    וני
    0.48
    òria
    0.46
    gares
    0.44
    وة
    0.44
    秽
    0.42
    리가
    0.42
     ressources
    0.41
     perspectiva
    0.40
    рты
    0.40
    óloga
    0.40
    POSITIVE LOGITS
     इनमें
    0.44
     (<
    0.43
    ইন
    0.41
     Jika
    0.40
     including
    0.38
    including
    0.38
     ইন
    0.38
     इधर
    0.38
     včetně
    0.37
    एयर
    0.37
    Activations Density 0.002%

    No Known Activations