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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 120577
    Prev
    Next
    INDEX
    Explanations

    technical terms and contexts

    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
    㝌
    0.44
    具体的な
    0.43
    詓
    0.42
    エンス
    0.42
    Succ
    0.42
    Schmidt
    0.41
    പ്പോള്‍
    0.41
    wärt
    0.41
    脩
    0.41
    apeutics
    0.40
    POSITIVE LOGITS
     user
    0.55
    params
    0.51
    db
    0.50
     db
    0.50
     params
    0.50
     controller
    0.47
    user
    0.47
     bbq
    0.43
     tribal
    0.41
     signer
    0.41
    Activations Density 0.000%

    No Known Activations