© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11229
    Prev
    Next
    INDEX
    Explanations

    documentation brief

    np_acts-logits-general · gemini-2.5-flash-lite

    line breaks or whitespace that precedes new sections, headings, or list items in structured documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     ocasião
    -1.70
     sicheren
    -1.59
     individuellen
    -1.54
     geholfen
    -1.54
     vollständ
    -1.52
     besseren
    -1.48
     üblichen
    -1.48
     trouxe
    -1.47
     schnellen
    -1.45
     ursprünglichen
    -1.45
    POSITIVE LOGITS
    ’
    1.67
     and
    1.59
    𖤍
    1.51
     enorme
    1.50
    called
    1.48
    嫆
    1.42
    /**
    1.40
     ainsi
    1.39
     ei
    1.38
     skak
    1.38
    Activations Density 0.003%

    No Known Activations