© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129485
    Prev
    Next
    INDEX
    Explanations

    resembling others

    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
     $\
    -1.35
    裢
    -1.30
     }}"></
    -1.28
     "
    -1.26
    .'”
    -1.25
     وهذا
    -1.24
    }>
    -1.24
     eloquent
    -1.24
    Спа
    -1.22
    Kemudian
    -1.20
    POSITIVE LOGITS
     others
    1.83
     resemble
    1.66
     resembling
    1.63
     resembles
    1.56
     other
    1.52
    like
    1.41
     like
    1.37
    儅
    1.36
     ...
    1.36
     utilisez
    1.31
    Activations Density 0.117%

    No Known Activations