© 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. 68648
    Prev
    Next
    INDEX
    Explanations

    rather than

    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
    こんな感じで
    -1.14
     två
    -1.10
    ご連絡
    -1.09
     kvinnor
    -1.08
    áneamente
    -1.07
    这种情况
    -1.06
     metade
    -1.05
    vgili
    -1.05
     modificaciones
    -1.04
    することができます
    -1.03
    POSITIVE LOGITS
     just
    1.64
     merely
    1.63
     simply
    1.56
     as
    1.45
     просто
    1.43
     only
    1.23
     apenas
    1.13
     solely
    1.08
    只是
    1.05
     только
    1.04
    Activations Density 0.019%

    No Known Activations