© 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. 10163
    Prev
    Next
    INDEX
    Explanations

    `clean()` and `.ivy2/`

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

    enumerate items in sequences

    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
    ዲ
    0.47
    Django
    0.42
    alignParent
    0.40
    django
    0.40
    ↵↵↵↵↵↵↵↵↵
    0.39
    BagConstraints
    0.39
    odhya
    0.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.38
     liaison
    0.38
     가능하다
    0.38
    POSITIVE LOGITS
     Limit
    0.46
     Help
    0.41
     Widget
    0.41
     Preserve
    0.40
     Basis
    0.40
    Basis
    0.40
    considered
    0.40
     Sheep
    0.39
     Complexes
    0.39
     Serving
    0.39
    Activations Density 0.006%

    No Known Activations