© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21635
    Prev
    Next
    INDEX
    Explanations

    code and key-value pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ...........
    -1.44
     意思
    -1.35
     .............
    -1.31
     ...............
    -1.30
     alltid
    -1.30
    rotter
    -1.29
     جدًا
    -1.28
    อยู่ใน
    -1.28
     every
    -1.27
     ..........
    -1.26
    POSITIVE LOGITS
     and
    1.78
     including
    1.71
     včetně
    1.45
     singkat
    1.34
    including
    1.30
    umably
    1.30
    ⬎
    1.30
    breviations
    1.30
    ัตว์
    1.30
     языку
    1.29
    Activations Density 0.010%

    No Known Activations