© 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. 131070
    Prev
    Next
    INDEX
    Explanations

    r words

    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_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
    ↵
    -3.23
    </strong>
    -3.17
    s
    -2.98
    e
    -2.81
     для
    -2.66
     моя
    -2.64
    曁
    -2.63
    i
    -2.58
    </u>
    -2.52
     قبل
    -2.42
    POSITIVE LOGITS
     was
    2.80
    一旁
    2.80
     '
    2.56
    齶
    2.45
    都快
    2.42
    詎
    2.42
    ?"
    2.34
    鲠
    2.30
    
    2.30
    dersfield
    2.30
    Activations Density 0.008%

    No Known Activations