© 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. 22-GEMMASCOPE-RES-131K
    7. 35998
    Prev
    Next
    INDEX
    Explanations

    quantifiers and comparisons

    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_22/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
    銹
    -1.02
    yship
    -0.99
    Verweise
    -0.98
    idable
    -0.96
    ckeye
    -0.92
    īb
    -0.92
    Figures
    -0.90
     for
    -0.89
     några
    -0.88
    了几
    -0.86
    POSITIVE LOGITS
     other
    2.22
     других
    1.61
     others
    1.41
     outras
    1.39
     anderen
    1.38
     similar
    1.31
     of
    1.30
     OTHER
    1.30
    other
    1.29
     دیگر
    1.28
    Activations Density 0.045%

    No Known Activations