© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 16903
    Prev
    Next
    INDEX
    Explanations

    parts of speech

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

    compound words and phrases

    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
     ||
    0.47
    \*
    0.45
    Á
    0.43
    Ç
    0.43
     &'
    0.42
    ','
    0.41
    amo
    0.41
    RI
    0.40
    q
    0.40
    ructor
    0.39
    POSITIVE LOGITS
     ampere
    1.02
     adenine
    1.01
     additionally
    0.81
    參数
    0.74
    黉
    0.71
     nonetheless
    0.69
     obtainable
    0.67
     nevertheless
    0.67
     furthermore
    0.66
     aforementioned
    0.64
    Activations Density 0.517%

    No Known Activations