© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 633
    Prev
    Next
    INDEX
    Explanations

    phrases starting with by

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

    by default, far, extension

    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
    ongoing
    0.37
     ◇
    0.36
    той
    0.36
     setTo
    0.36
    }$}
    0.35
    他にも
    0.33
    才能
    0.33
     싶은
    0.33
     Meaning
    0.32
    ствует
    0.32
    POSITIVE LOGITS
     virtue
    1.35
    zantine
    1.08
     dint
    1.03
     means
    0.90
     way
    0.82
    衷
    0.82
     default
    0.79
     mistake
    0.79
    products
    0.76
    zant
    0.75
    Activations Density 0.268%

    No Known Activations