© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15261
    Prev
    Next
    INDEX
    Explanations

    legal exemptions and affidavits

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

    specific instructions or scenarios

    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_31_width_262k_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
    食材
    0.47
    女
    0.44
    வசாய
    0.43
    服务端
    0.43
    金融
    0.42
     வாழ்
    0.42
    𝓂
    0.42
    THz
    0.41
    뮤
    0.41
    静态
    0.40
    POSITIVE LOGITS
     affidavits
    0.57
     вело
    0.51
     suspensions
    0.50
     exemptions
    0.48
     inapplicable
    0.48
     insufficiently
    0.46
     специальных
    0.46
     omissions
    0.46
     Exempt
    0.46
     perjury
    0.46
    Activations Density 0.000%

    No Known Activations