© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100542
    Prev
    Next
    INDEX
    Explanations

    strontium, iten, strony

    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
    Before
    -2.63
     Before
    -2.55
     When
    -2.48
    <
    -2.48
    Even
    -2.33
    1
    -2.33
    Going
    -2.31
    Two
    -2.31
    When
    -2.30
    Not
    -2.27
    POSITIVE LOGITS
    黾
    3.20
     soooo
    3.13
    ſſen
    3.03
    ensitive
    2.80
    
    2.77
     sooo
    2.75
    
    2.73
    
    2.70
    ৢ
    2.70
    
    2.69
    Activations Density 0.002%

    No Known Activations