© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84915
    Prev
    Next
    INDEX
    Explanations

    section identifiers or citations

    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
    c
    -1.05
    ac
    -0.98
    wi
    -0.92
    p
    -0.89
    合わない
    -0.87
    ea
    -0.87
    两次
    -0.85
    ister
    -0.84
     aveva
    -0.84
    j
    -0.84
    POSITIVE LOGITS
    samsung
    0.90
     like
    0.89
    辑
    0.88
     BaseController
    0.84
     家具
    0.82
    ogener
    0.82
    szer
    0.81
    큽
    0.81
    utusan
    0.80
     its
    0.80
    Activations Density 0.028%

    No Known Activations