© 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. 43944
    Prev
    Next
    INDEX
    Explanations

    protection and being protected

    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
    𝘪
    -1.25
     should
    -1.21
     seharusnya
    -1.20
     whether
    -1.16
     polecam
    -1.15
     mengikut
    -1.14
     mengenai
    -1.13
     mencer
    -1.13
     distinción
    -1.12
     about
    -1.10
    POSITIVE LOGITS
    ’
    1.63
     “
    1.24
     "
    1.17
    ”-
    1.13
    )’
    1.12
    }$
    1.11
    ’”
    1.09
    ↵↵↵↵
    1.08
    ands
    1.07
    稍
    1.06
    Activations Density 0.033%

    No Known Activations