© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 5889
    Prev
    Next
    INDEX
    Explanations

    explains core concepts and mechanics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
     verbal
    0.86
     Лі
    0.84
     ,
    0.82
    还有
    0.82
     Verbal
    0.82
    ”,
    0.81
     onay
    0.81
    Мне
    0.80
    也要
    0.80
     velas
    0.80
    POSITIVE LOGITS
     প্রকৃতপক্ষে
    0.99
    шинство
    0.85
    🤯
    0.81
     enorme
    0.81
     এটিকে
    0.80
    이는
    0.79
     چنانچہ
    0.79
    سمى
    0.79
     있기
    0.78
     일반적으로
    0.78
    Activations Density 0.259%

    No Known Activations