© 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. 40-GEMMASCOPE-2-RES-65K
    7. 53854
    Prev
    Next
    INDEX
    Explanations

    invitation and being invited

    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_65k_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
    镕
    0.39
    翕
    0.38
    定位
    0.38
     actively
    0.37
     активно
    0.37
     확실
    0.37
    рован
    0.36
     চিত
    0.36
     defens
    0.36
    ㅝ
    0.36
    POSITIVE LOGITS
    邀请
    1.42
     invite
    1.39
     invites
    1.38
     invitations
    1.34
     invited
    1.30
     invitation
    1.28
    邀請
    1.27
    invite
    1.25
     пригла
    1.23
     Invite
    1.23
    Activations Density 0.019%

    No Known Activations