© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5014
    Prev
    Next
    INDEX
    Explanations

    storage and destination nouns

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

    output to files or screen

    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_262k_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
     औष
    0.46
     कामगिरी
    0.45
     mùi
    0.43
    ármaz
    0.42
     Besuch
    0.42
    遶
    0.41
     শুটিং
    0.41
     स्वातंत्र
    0.40
    镖
    0.40
    沍
    0.40
    POSITIVE LOGITS
     coffers
    0.74
     inbox
    0.66
     repositories
    0.60
     boxes
    0.59
     shelves
    0.58
     pockets
    0.58
     containers
    0.57
     notebooks
    0.57
     baskets
    0.57
     cupboards
    0.57
    Activations Density 0.421%

    No Known Activations