© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185176
    Prev
    Next
    INDEX
    Explanations

    committees

    np_acts-logits-general · gemini-2.5-flash-lite

    excited, truly, to, tool, stain, happy, decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     који
    0.55
     jarring
    0.48
     пово
    0.46
    toBeTruthy
    0.45
     որ
    0.45
    clearRect
    0.44
     който
    0.44
     प्रचंड
    0.43
     탄
    0.43
     crumpled
    0.43
    POSITIVE LOGITS
    ח
    0.58
    ロ
    0.54
    旦
    0.53
    ്ര
    0.51
     residues
    0.50
    ラ
    0.48
    ኡ
    0.48
    درا
    0.47
    h
    0.47
    測
    0.47
    Activations Density 0.000%

    No Known Activations