© 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. 8434
    Prev
    Next
    INDEX
    Explanations

    numbers after text

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

    2G, 3G, 4G, 5G

    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
    ５
    0.52
    ８
    0.50
     seventy
    0.49
    ７
    0.47
    ❽
    0.47
     eighty
    0.46
     Seventy
    0.46
    thirty
    0.45
    𝟖
    0.45
     ninety
    0.45
    POSITIVE LOGITS
     plupart
    0.35
    ეს
    0.34
     接
    0.34
    Majority
    0.34
     вообще
    0.34
     boost
    0.34
     విశ
    0.33
     cart
    0.33
     কিছুই
    0.33
     Tenerife
    0.33
    Activations Density 0.103%

    No Known Activations