© 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. 17870
    Prev
    Next
    INDEX
    Explanations

    citations, versions, dates

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

    numbers or ordinals

    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
    inato
    0.38
     JAC
    0.37
    ໋
    0.36
    UTURE
    0.36
     kuu
    0.35
     FOREIGN
    0.34
     rud
    0.34
    тап
    0.34
     (++
    0.33
     ro
    0.33
    POSITIVE LOGITS
    Scores
    0.40
     जानवरों
    0.38
    邂
    0.38
    ্ল
    0.36
     আসে
    0.36
    बॉ
    0.36
    nomes
    0.36
    生命的
    0.36
    दिशा
    0.36
    方向
    0.35
    Activations Density 0.098%

    No Known Activations