© 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. 53-GEMMASCOPE-2-RES-65K
    7. 755
    Prev
    Next
    INDEX
    Explanations

    of your beliefs

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

    list of negative or creative terms

    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
    XXXX
    0.32
    plus
    0.31
    빕
    0.31
    до
    0.29
    ר
    0.28
    ча
    0.28
    р
    0.28
    ח
    0.28
    0
    0.27
    ાઇ
    0.27
    POSITIVE LOGITS
     gahet
    0.27
     azúcar
    0.27
     ourselves
    0.26
     powerAll
    0.26
     condensing
    0.26
     seguenti
    0.26
     río
    0.26
     heath
    0.26
    র্জন
    0.25
    対流
    0.25
    Activations Density 0.339%

    No Known Activations