© 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. 34-GEMMASCOPE-RES-131K
    7. 84770
    Prev
    Next
    INDEX
    Explanations

    On followed by constructions

    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_34/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
    これは
    -1.18
    を
    -0.92
    の
    -0.88
    や
    -0.88
    OUR
    -0.85
    的
    -0.84
    čnosti
    -0.82
    ว่า
    -0.82
    つまり
    -0.82
    KS
    -0.80
    POSITIVE LOGITS
     behalf
    1.06
     purpose
    0.95
     contrary
    0.94
     basis
    0.93
     demand
    0.92
    うえ
    0.92
    ulada
    0.91
     verge
    0.90
    PURPOSE
    0.90
     occasions
    0.88
    Activations Density 0.103%

    No Known Activations