© 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. 112696
    Prev
    Next
    INDEX
    Explanations

    text inside backticks

    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
     brand
    0.44
    는
    0.44
     branded
    0.43
     Brand
    0.42
     biographical
    0.42
     브랜드
    0.42
     portrait
    0.41
     text
    0.40
     commer
    0.40
     SAR
    0.40
    POSITIVE LOGITS
    ,\\
    0.54
    ,
    0.50
    ObjectMapper
    0.49
    ძლიათ
    0.48
    ubarb
    0.48
    Jh
    0.48
    ایی
    0.47
    oarthritis
    0.47
    ajal
    0.45
    deh
    0.45
    Activations Density 0.004%

    No Known Activations