© 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. 56943
    Prev
    Next
    INDEX
    Explanations

    conditional statements and lack

    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
    Dairy
    0.51
    ై
    0.50
    логи
    0.46
    Lock
    0.45
    PlatformImage
    0.45
    Cuánt
    0.44
     आपल्याला
    0.43
    া
    0.43
     приме
    0.42
    <unused53>
    0.42
    POSITIVE LOGITS
     not
    0.54
     is
    0.52
     Not
    0.49
     or
    0.48
     markdown
    0.46
     tod
    0.44
     papers
    0.44
     November
    0.44
     Markdown
    0.44
     by
    0.43
    Activations Density 0.007%

    No Known Activations