© 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. 31-GEMMASCOPE-2-RES-262K
    7. 4940
    Prev
    Next
    INDEX
    Explanations

    make or making something

    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_262k_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
    4
    0.38
    2
    0.36
    5
    0.35
    6
    0.33
    when
    0.31
    0
    0.31
    І
    0.30
    า
    0.30
    ।
    0.29
     vremena
    0.29
    POSITIVE LOGITS
     sure
    0.43
     it
    0.39
     amends
    0.36
     make
    0.36
     decisions
    0.34
     up
    0.32
    hift
    0.31
     headlines
    0.29
     everything
    0.29
    ه
    0.29
    Activations Density 0.083%

    No Known Activations