© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26987
    Prev
    Next
    INDEX
    Explanations

    be followed by consequence or state

    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
     în
    0.42
     ở
    0.42
     in
    0.41
     n
    0.40
    Davis
    0.40
     Curiosity
    0.40
     museums
    0.38
     be
    0.38
     Davis
    0.38
     subset
    0.37
    POSITIVE LOGITS
    с
    0.49
     painful
    0.47
    eb
    0.45
    тове
    0.45
    𝔯
    0.45
    кло
    0.45
     военных
    0.44
    ⓢ
    0.43
    一道
    0.43
    ⑤
    0.42
    Activations Density 0.039%

    No Known Activations