© 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. 2207
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns

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

    C64 positive descriptions

    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
    achios
    0.30
    るので
    0.28
     plexus
    0.28
     Ising
    0.28
    𝐀
    0.27
    skcipher
    0.27
     stoi
    0.26
     gradio
    0.26
     همان
    0.26
     தன்
    0.26
    POSITIVE LOGITS
    ‌و
    0.26
    ‌
    0.26
    ‌.
    0.26
     incumbent
    0.25
     Strange
    0.25
     debacle
    0.24
    ‌‌
    0.24
    发布的
    0.24
     수요
    0.24
    대의
    0.23
    Activations Density 0.427%

    No Known Activations