© 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. 3388
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence terminators

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

    bullet points and lists

    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
     แห่ง
    0.32
    —
    0.30
     -
    0.29
     différentes
    0.29
     了
    0.28
     /
    0.28
    에서의
    0.27
    ...
    0.27
     unseres
    0.27
    Finder
    0.27
    POSITIVE LOGITS
    #$%
    0.43
    warning
    0.40
    ̼
    0.37
    jpg
    0.37
    ‍♀️
    0.37
    ̮
    0.37
    ᐟ
    0.37
    >.
    0.36
    ></
    0.35
    彡
    0.35
    Activations Density 0.260%

    No Known Activations