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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47559
    Prev
    Next
    INDEX
    Explanations

    in a followed by descriptive word

    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
     same
    -2.34
     when
    -2.30
     but
    -2.09
     with
    -1.96
    in
    -1.94
     only
    -1.86
    on
    -1.85
     on
    -1.77
    man
    -1.77
     not
    -1.73
    POSITIVE LOGITS
    ꜆
    1.98
    ꪻ
    1.89
    鹩
    1.85
     vont
    1.84
    ᥀
    1.80
    gning
    1.80
     :"
    1.80
     beſ
    1.71
     accidente
    1.70
     essi
    1.70
    Activations Density 0.031%

    No Known Activations