© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 16948
    Prev
    Next
    INDEX
    Explanations

    make decisions

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

    description words

    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_53_width_65k_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
     pédicule
    0.39
     layi
    0.39
     aloud
    0.38
     całość
    0.38
     raid
    0.37
    Rồi
    0.37
    𝑇
    0.37
    Leader
    0.36
     வாக்கு
    0.36
    雷
    0.36
    POSITIVE LOGITS
     Accepting
    0.50
    nets
    0.38
     Projects
    0.38
    cione
    0.37
    鬟
    0.37
     projects
    0.36
     dealings
    0.36
     Elephant
    0.36
    bearers
    0.36
     Jillian
    0.36
    Activations Density 0.000%

    No Known Activations