© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3691
    Prev
    Next
    INDEX
    Explanations

    just or less quantity

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

    not just

    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
     వరకు
    0.48
    )>=
    0.41
     >
    0.39
     Preferably
    0.39
    越大
    0.39
    至少
    0.39
    ⊇
    0.39
    supseteq
    0.38
     (>
    0.38
    有一定的
    0.37
    POSITIVE LOGITS
     just
    2.44
     less
    2.27
     মাত্র
    2.23
    just
    2.20
     महज
    2.13
     menos
    2.02
     apenas
    2.00
    Less
    1.98
    เพียง
    1.93
     Less
    1.91
    Activations Density 0.392%

    No Known Activations