© 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. 16-GEMMASCOPE-2-RES-262K
    7. 8804
    Prev
    Next
    INDEX
    Explanations

    introducing noted facts

    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_16_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
    ၀
    0.90
     Translations
    0.84
    𝟎
    0.83
    ០
    0.79
    ون
    0.79
     Induction
    0.79
     Alternatively
    0.79
    ০১
    0.79
     l
    0.78
     Sacrifice
    0.78
    POSITIVE LOGITS
    も
    1.24
     noted
    1.19
    在
    1.18
     in
    1.13
    ą
    1.02
     noting
    1.00
    nya
    1.00
    ও
    0.98
    ใน
    0.97
     σε
    0.96
    Activations Density 0.004%

    No Known Activations