© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10925
    Prev
    Next
    INDEX
    Explanations

    holes and openings

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

    holes, gaps, rifts

    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_40_width_16k_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
    ക്കൾ
    0.44
    тек
    0.41
    逦
    0.41
    verband
    0.40
    桿
    0.40
     jang
    0.39
     weights
    0.39
    Folding
    0.38
    缨
    0.38
     भार
    0.38
    POSITIVE LOGITS
     holes
    2.30
     hole
    2.28
     Holes
    2.11
     Hole
    2.06
     отверсти
    2.02
    穴
    1.99
    holes
    1.95
    hole
    1.95
    孔
    1.58
     lỗ
    1.55
    Activations Density 0.530%

    No Known Activations