© 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-65K
    7. 13730
    Prev
    Next
    INDEX
    Explanations

    Context; loaded, lifespan,

    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_65k_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
    Ge
    0.44
     grandparents
    0.42
    ↵↵
    0.42
     nbsp
    0.41
    package
    0.40
    You
    0.39
     स्ने
    0.39
    Trusted
    0.39
    更大
    0.39
    包括
    0.38
    POSITIVE LOGITS
     nouve
    0.50
     lecteur
    0.49
     musik
    0.45
     musicales
    0.44
     monumento
    0.44
     lecteurs
    0.43
    栱
    0.42
     fenomen
    0.42
     rôle
    0.42
    दों
    0.41
    Activations Density 0.000%

    No Known Activations