© 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. 6660
    Prev
    Next
    INDEX
    Explanations

    numbers and slashes

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

    variables like `r`, `n`, `i`, `a`, `ptr`

    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
    🇩
    0.44
    Surprisingly
    0.40
    Alle
    0.39
    𒂊
    0.39
    Often
    0.39
    娃
    0.39
    Like
    0.38
     свадь
    0.38
    ️
    0.38
    Today
    0.38
    POSITIVE LOGITS
    ṇ
    0.43
    =='
    0.40
    represented
    0.40
     ``
    0.39
    "/"
    0.38
    increment
    0.38
    ))(
    0.38
    denoted
    0.38
    ``.
    0.38
    īs
    0.38
    Activations Density 0.028%

    No Known Activations