© 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. 22-GEMMASCOPE-RES-131K
    4. 217
    Prev
    Next
    INDEX
    Explanations

    facts details revealed mystery secret changes

    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
     both
    -1.15
    Kontra
    -1.05
    Karakter
    -1.01
    Dimensi
    -0.99
     like
    -0.99
     more
    -0.99
     with
    -0.97
     像
    -0.97
     susu
    -0.97
     persa
    -0.97
    POSITIVE LOGITS
    ylation
    1.23
     ainda
    1.09
    ra
    1.05
    atization
    1.02
    E
    1.01
     todavía
    1.01
    ari
    0.99
    regarding
    0.99
    R
    0.98
    竟然是
    0.98
    Activations Density 0.021%

    No Known Activations