© 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. 14385
    Prev
    Next
    INDEX
    Explanations

    . where you to

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

    increase, or changes over time

    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
     He
    0.50
     ppl
    0.49
     yells
    0.48
    🤬
    0.47
    一开始
    0.46
    ulating
    0.46
     humili
    0.46
     shri
    0.46
     shouts
    0.45
    🤷
    0.45
    POSITIVE LOGITS
    liquer
    0.46
    ضو
    0.46
    гона
    0.45
     さ
    0.44
    鳴
    0.44
     antioxidant
    0.43
     міні
    0.43
     integrative
    0.42
     పని
    0.42
     సర
    0.42
    Activations Density 0.006%

    No Known Activations