© 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. 50862
    Prev
    Next
    INDEX
    Explanations

    descriptive sequences

    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
    Enhanced
    0.42
     всі
    0.42
    滙
    0.41
    簡
    0.40
    頹
    0.40
     Umbrella
    0.39
    ObjectClass
    0.39
    Design
    0.38
     които
    0.38
    庸
    0.38
    POSITIVE LOGITS
     biomark
    0.44
     tí
    0.44
     proyección
    0.44
     থেকে
    0.44
     pertanian
    0.44
     dönd
    0.43
     Monday
    0.43
    ról
    0.43
     pracę
    0.43
     ferrovi
    0.43
    Activations Density 0.005%

    No Known Activations