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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 5402
    Prev
    Next
    INDEX
    Explanations

    docstrings and code structure

    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_40_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
    ={$
    0.52
     સંપૂર્ણ
    0.48
     수출
    0.48
    iftoire
    0.48
     gouttes
    0.47
    httpClient
    0.46
    隴
    0.46
    enumValues
    0.45
    {$
    0.45
    Exports
    0.45
    POSITIVE LOGITS
     Python
    1.90
    Python
    1.77
     python
    1.71
    python
    1.61
     PYTHON
    1.27
     NumPy
    1.27
    PYTHON
    1.27
     isinstance
    1.23
     Py
    1.22
     pygame
    1.15
    Activations Density 0.213%

    No Known Activations