© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 670
    Prev
    Next
    INDEX
    Explanations

    H-starting words

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

    words starting with h

    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
    牞
    0.46
    ្វី
    0.45
     strListName
    0.45
     старосног
    0.42
    蓼
    0.42
    
    0.42
     کمک
    0.41
    ૄ
    0.41
    澪
    0.41
    受伤
    0.39
    POSITIVE LOGITS
     H
    1.66
     ஹ
    1.52
    H
    1.50
    Ｈ
    1.50
     HC
    1.49
     HB
    1.42
     h
    1.41
     ഹ
    1.38
     HF
    1.38
     ჰ
    1.38
    Activations Density 0.873%

    No Known Activations