© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14612
    Prev
    Next
    INDEX
    Explanations

    describing characteristics with "has"

    np_acts-logits-general · gemini-2.5-flash-lite

    one or specific counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     death
    0.48
    family
    0.44
    ↵↵
    0.44
     family
    0.44
     como
    0.44
     continuing
    0.43
     impacted
    0.43
    ​​​​
    0.43
     children
    0.42
     recorded
    0.42
    POSITIVE LOGITS
    猞
    0.48
    嫄
    0.48
     PROGRAMS
    0.48
    INTa
    0.48
     науш
    0.47
     листа
    0.46
     Programmes
    0.46
     گوش
    0.46
     slto
    0.46
    赭
    0.46
    Activations Density 0.001%

    No Known Activations