© 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. 13508
    Prev
    Next
    INDEX
    Explanations

    self-related nouns

    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
    .
    -3.02
     is
    -2.45
     vijf
    -2.23
     outras
    -2.17
     REALLY
    -2.06
    }$
    -2.02
     sooo
    -2.00
    了他的
    -1.98
     diversos
    -1.95
     dando
    -1.95
    POSITIVE LOGITS
     supremely
    2.66
     burgeoning
    2.52
     cheerful
    2.48
     immensely
    2.47
     plethora
    2.39
     unrelenting
    2.39
    。
    2.33
     weirdly
    2.25
     enticing
    2.22
     exquisitely
    2.22
    Activations Density 0.016%

    No Known Activations