© 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. 42431
    Prev
    Next
    INDEX
    Explanations

    wave of

    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
    on
    -1.75
    1
    -1.64
    and
    -1.57
    </h1>
    -1.51
    in
    -1.48
     technischen
    -1.47
     schützen
    -1.47
     тук
    -1.40
     conséquent
    -1.38
    assment
    -1.38
    POSITIVE LOGITS
    ть
    1.49
    彀
    1.42
    áciu
    1.42
    酒吧
    1.41
    我说
    1.37
     lavabo
    1.36
    ме
    1.34
    ঙ
    1.34
    쐈
    1.33
     maris
    1.28
    Activations Density 0.025%

    No Known Activations