© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8372
    Prev
    Next
    INDEX
    Explanations

    page numbers and ranges

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

    items numbered in sections

    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
    Negative Logits
    頁
    0.38
     Page
    0.37
    BEST
    0.36
     confe
    0.34
    +%
    0.33
    POP
    0.33
    LAMP
    0.33
    OCE
    0.32
    KB
    0.32
     sostit
    0.31
    POSITIVE LOGITS
    리를
    0.41
     Hitler
    0.40
    वतात
    0.40
     strangely
    0.39
    入れて
    0.38
    ట్టిన
    0.37
     Surprisingly
    0.37
    ፉ
    0.37
     होत्या
    0.36
     कलाकारों
    0.36
    Activations Density 0.039%

    No Known Activations