© 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. 171842
    Prev
    Next
    INDEX
    Explanations

    install disable

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

    widespread majority value snippet

    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
     oeste
    0.58
    维
    0.54
     üç
    0.51
     wales
    0.51
     usu
    0.49
    セ
    0.49
    𝚖
    0.49
     southwest
    0.48
     wits
    0.48
     cooper
    0.48
    POSITIVE LOGITS
    }~\
    0.50
    অপহরণ
    0.46
    }]$.
    0.45
    Into
    0.44
    Foreground
    0.43
    原子力
    0.43
     لماذا
    0.42
    Environmental
    0.42
     বোধ
    0.41
    ুগত্য
    0.41
    Activations Density 0.000%

    No Known Activations