© 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. 34-GEMMASCOPE-RES-131K
    4. 94044
    Prev
    Next
    INDEX
    Explanations

    "how to" or proper nouns starting with "how"

    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_34/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
    こちらは
    -0.91
    あなたは
    -0.88
    機種
    -0.87
    ですが
    -0.83
    あなた
    -0.82
    が
    -0.81
    食器
    -0.80
    「
    -0.80
    収入
    -0.80
    Durée
    -0.80
    POSITIVE LOGITS
    itzer
    1.38
    ITZER
    1.34
    Stuff
    1.29
     many
    1.21
     much
    1.16
    soever
    1.08
    ards
    1.07
     to
    1.07
    ells
    1.03
    beit
    1.03
    Activations Density 0.065%

    No Known Activations