© 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. 31-GEMMASCOPE-2-RES-262K
    7. 50397
    Prev
    Next
    INDEX
    Explanations

    words before common words

    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_31_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
    s
    0.46
    子
    0.44
    த்து
    0.40
    derivative
    0.39
    obedience
    0.39
    last
    0.38
     যতক্ষণ
    0.38
    sentence
    0.38
    久し
    0.38
    ッ
    0.38
    POSITIVE LOGITS
     Metern
    0.44
     Wouldn
    0.42
     ennen
    0.42
     trebui
    0.41
    frees
    0.41
    ihal
    0.40
     diesem
    0.39
    णाल
    0.39
     wirken
    0.39
    牖
    0.39
    Activations Density 0.011%

    No Known Activations