© 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. 21411
    Prev
    Next
    INDEX
    Explanations

    I, we, us, me, you identifying actions

    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
     their
    -1.62
    ༛
    -1.51
     própri
    -1.49
    ་་
    -1.48
     also
    -1.45
    The
    -1.29
    ggy
    -1.28
    觏
    -1.28
     its
    -1.27
     >",
    -1.24
    POSITIVE LOGITS
     Это
    1.38
     такая
    1.27
     climático
    1.21
     ALWAYS
    1.21
     сделал
    1.18
     vedno
    1.17
    このような
    1.11
    方には
    1.11
     möjlighet
    1.11
    深い
    1.10
    Activations Density 0.116%

    No Known Activations