© 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. 53966
    Prev
    Next
    INDEX
    Explanations

    keywords followed by descriptions

    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
     and
    -1.37
     which
    -1.22
     it
    -1.09
    fordshire
    -1.06
    ))).
    -1.03
    oused
    -0.98
    ництва
    -0.96
    føre
    -0.95
    付近
    -0.94
    artment
    -0.94
    POSITIVE LOGITS
     steadily
    1.16
     slowly
    1.13
    querade
    1.09
    Really
    1.09
     really
    1.09
    aka
    1.08
     veramente
    1.08
     estremamente
    1.07
     davvero
    1.07
     Really
    1.06
    Activations Density 0.059%

    No Known Activations