© 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. 70368
    Prev
    Next
    INDEX
    Explanations

    the followed by proper 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
     rangs
    -1.66
    Подроб
    -1.54
    Читать
    -1.53
    Leírás
    -1.52
    췄
    -1.50
     antici
    -1.49
    pires
    -1.48
    Вопрос
    -1.45
    knows
    -1.45
     formen
    -1.44
    POSITIVE LOGITS
     \
    1.74
    .
    1.59
     Department
    1.58
     is
    1.52
    </b>
    1.48
    у
    1.44
     However
    1.43
    irs
    1.42
    _
    1.40
    ]}\
    1.39
    Activations Density 0.159%

    No Known Activations