© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14065
    Prev
    Next
    INDEX
    Explanations

    don't interrupt conversation

    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_16k_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
     enk
    0.48
     اعلان
    0.43
     battered
    0.42
     incar
    0.40
    Notify
    0.39
    APR
    0.38
     aerosol
    0.38
     암
    0.38
     работо
    0.38
     arbet
    0.38
    POSITIVE LOGITS
     Conversation
    0.89
     conversational
    0.89
     conversación
    0.89
     conversation
    0.88
    Conversation
    0.82
    conversation
    0.79
     conversa
    0.78
     কথোপকথ
    0.78
     Conversations
    0.78
     interviewer
    0.77
    Activations Density 0.708%

    No Known Activations