© 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. 10-GEMMASCOPE-RES-131K
    4. 9358
    Prev
    Next
    INDEX
    Explanations

    starting from

    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
    >
    -1.94
    From
    -1.84
    Two
    -1.78
    Before
    -1.71
    Both
    -1.67
     From
    -1.64
    When
    -1.62
    B
    -1.59
    .
    -1.57
    Four
    -1.55
    POSITIVE LOGITS
    憷
    1.94
    翃
    1.78
    迓
    1.75
    反抗
    1.59
     nové
    1.59
     revolución
    1.59
     división
    1.58
    
    1.55
    ズニー
    1.52
     světě
    1.52
    Activations Density 0.007%

    No Known Activations