© 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-16K
    7. 2728
    Prev
    Next
    INDEX
    Explanations

    Reuters sources

    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
    ​​​​
    0.34
    TikTok
    0.33
    Zara
    0.31
     Twitter
    0.31
     Monday
    0.31
     Tuesday
    0.30
     Isaiah
    0.30
     गुरुवार
    0.29
    Thursday
    0.29
    प
    0.29
    POSITIVE LOGITS
     curvatures
    0.37
     liquors
    0.36
     sediments
    0.35
     canvases
    0.34
     pelvis
    0.33
     lotions
    0.33
     rugs
    0.32
     bends
    0.32
     sheaves
    0.32
     appendages
    0.31
    Activations Density 0.002%

    No Known Activations