© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5477
    Prev
    Next
    INDEX
    Explanations

    conversation and discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_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
     link
    0.79
    link
    0.75
     Link
    0.74
     hyperlink
    0.73
    Link
    0.73
     IgM
    0.68
     submission
    0.65
    징
    0.64
     links
    0.63
     لينك
    0.62
    POSITIVE LOGITS
     conversation
    2.81
     conversations
    2.71
     Conversation
    2.63
    Conversation
    2.61
     Conversations
    2.45
     discussion
    2.43
     discussions
    2.40
    conversation
    2.33
     dialogue
    2.29
     Discussion
    2.28
    Activations Density 1.025%

    No Known Activations