Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 422
    Prev
    Next
    INDEX
    Explanations

    squared terms

    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_40_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
     embark
    0.42
    जुर्ग
    0.39
    唿
    0.38
     discounted
    0.37
     greenery
    0.37
     commotion
    0.36
    ⤥
    0.36
     thổi
    0.36
     തൊഴിലാ
    0.36
    textured
    0.35
    POSITIVE LOGITS
     squared
    1.09
    ²
    0.98
    squared
    0.97
    ²,
    0.93
     제곱
    0.91
    ².
    0.89
     Squared
    0.84
    ²)
    0.81
    平方
    0.78
    Squared
    0.77
    Activations Density 0.029%

    No Known Activations