© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21129
    Prev
    Next
    INDEX
    Explanations

    deep, depth, deeply, deep state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    㕵
    0.45
     pumped
    0.43
    сов
    0.42
     অভিহিত
    0.41
    らし
    0.41
    pump
    0.40
     треть
    0.40
    सेस
    0.40
    बू
    0.39
     జీ
    0.39
    POSITIVE LOGITS
     deep
    1.06
    深
    1.06
     깊
    1.02
    깊
    1.00
     profunda
    0.99
     Deep
    0.98
     profund
    0.98
     profond
    0.96
     глубо
    0.96
     profundo
    0.95
    Activations Density 0.018%

    No Known Activations