© 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. 128544
    Prev
    Next
    INDEX
    Explanations

    sons and daughters, illustrious, produced

    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
    ஂ
    -1.80
     or
    -1.45
    อื่น
    -1.41
    莳
    -1.41
     bäst
    -1.38
    đầm
    -1.37
     säll
    -1.36
    Sudah
    -1.36
     visst
    -1.36
    Sekarang
    -1.34
    POSITIVE LOGITS
     of
    2.28
    s
    1.66
     angep
    1.61
    unfortunately
    1.55
     to
    1.52
     Nuevas
    1.45
     Quando
    1.45
     WIL
    1.44
     übernommen
    1.44
     renowned
    1.41
    Activations Density 0.014%

    No Known Activations