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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73191
    Prev
    Next
    INDEX
    Explanations

    relative importance, determined, Flying, Patterns, genotypes, old

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific paper formatting elements, particularly punctuation at the end of titles and abstracts in academic publications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    (/^
    -1.55
     then
    -1.53
    ervant
    -1.47
     bolsillos
    -1.45
     cordones
    -1.38
     رایگان
    -1.36
    ggere
    -1.34
     {$\
    -1.33
    ifiers
    -1.33
    licitations
    -1.32
    POSITIVE LOGITS
     besonders
    1.63
     which
    1.58
    Other
    1.51
    During
    1.48
     jsem
    1.47
     bereits
    1.45
    Its
    1.44
    曖昧さ回避
    1.41
     old
    1.41
    Through
    1.39
    Activations Density 0.944%

    No Known Activations