© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3010
    Prev
    Next
    INDEX
    Explanations

    theological discourse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     injective
    0.64
     pakas
    0.62
     capill
    0.60
    MaskInto
    0.60
    ظيم
    0.60
    滀
    0.59
     neutroph
    0.59
    រូប
    0.59
    INFRINGEMENT
    0.58
    耸
    0.58
    POSITIVE LOGITS
     conversation
    4.92
     conversations
    4.61
     Conversation
    4.34
     discussion
    4.31
    conversation
    4.23
    Conversation
    4.20
     discussions
    4.12
     conversación
    3.97
     Conversations
    3.95
     conversa
    3.87
    Activations Density 1.975%

    No Known Activations