© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 39889
    Prev
    Next
    INDEX
    Explanations

    origin or provision

    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
    ید
    0.86
     
    0.79
    ун
    0.79
    اري
    0.79
    о
    0.75
    е
    0.75
    もら
    0.71
    льного
    0.69
     stylized
    0.68
     изучение
    0.66
    POSITIVE LOGITS
     sources
    1.12
     Sources
    1.11
     fonti
    1.00
     źród
    0.98
    f
    0.95
     fontes
    0.92
     Source
    0.91
     SOURCES
    0.89
    a
    0.88
    Sources
    0.88
    Activations Density 0.047%

    No Known Activations