© 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. 22-GEMMASCOPE-RES-131K
    7. 14773
    Prev
    Next
    INDEX
    Explanations

    company names and corporate suffixes

    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
     that
    -1.84
     such
    -1.52
     This
    -1.42
    様な
    -1.41
     this
    -1.40
    を行います
    -1.39
    J
    -1.38
    為に
    -1.34
     the
    -1.34
    N
    -1.32
    POSITIVE LOGITS
    などが
    1.66
    などは
    1.44
     Ltd
    1.38
    が上が
    1.34
     chè
    1.33
     pérd
    1.33
     impecable
    1.33
     maig
    1.32
    pilih
    1.31
    还是很
    1.30
    Activations Density 0.092%

    No Known Activations