© 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. 14497
    Prev
    Next
    INDEX
    Explanations

    our, best, limited, help

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

    list items describing strategies and qualities

    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
     Dari
    0.47
     Gore
    0.44
     Worte
    0.44
    .].
    0.41
     Lui
    0.41
    чется
    0.40
    citing
    0.39
     Cái
    0.39
     Créd
    0.39
     Moira
    0.38
    POSITIVE LOGITS
     secondaires
    0.42
    सीएम
    0.40
    經常
    0.40
     अक्सर
    0.39
     reciben
    0.39
    +
    0.39
    Focus
    0.39
    FOCUS
    0.38
    ালক
    0.38
     agregar
    0.37
    Activations Density 0.001%

    No Known Activations