© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11931
    Prev
    Next
    INDEX
    Explanations

    GitHub commit and issue management

    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_31_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
    perceptron
    0.59
    storage
    0.53
     хранения
    0.50
    応用
    0.49
    産業
    0.49
    calcul
    0.48
    <unused1033>
    0.47
    計算
    0.47
     calcula
    0.47
    絃
    0.47
    POSITIVE LOGITS
     GitHub
    0.66
     Markdown
    0.65
     Contributing
    0.63
     GitLab
    0.61
     Jira
    0.61
     README
    0.60
     Technical
    0.59
     Workflow
    0.57
     Documentation
    0.57
     Tickets
    0.55
    Activations Density 0.057%

    No Known Activations