© 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. 3533
    Prev
    Next
    INDEX
    Explanations

    Europa and Enceladus

    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
     act
    0.46
    相当于
    0.45
     oct
    0.44
    验证
    0.44
     Poo
    0.44
     knack
    0.42
    पू
    0.42
    霍
    0.41
     পড়েছে
    0.41
     Ho
    0.40
    POSITIVE LOGITS
    europe
    0.47
     وګ
    0.47
    simply
    0.46
    ೬
    0.45
    such
    0.43
    ять
    0.43
    dropped
    0.42
    applying
    0.42
    ili
    0.42
    lives
    0.41
    Activations Density 0.001%

    No Known Activations