© 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. 118123
    Prev
    Next
    INDEX
    Explanations

    managing complex features

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

    character attack, Wild Hunt, relationship

    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
     pariy
    0.57
    avaliacao
    0.47
     يوجد
    0.45
    ]
    0.45
     ദു
    0.45
    ]::-
    0.45
    aksikan
    0.43
    ২৮
    0.42
    devDependencies
    0.42
    ]\
    0.42
    POSITIVE LOGITS
     Return
    0.48
    METAL
    0.47
    refer
    0.46
    快適
    0.46
    ンの
    0.46
    са
    0.45
     return
    0.44
    soy
    0.44
    றிவு
    0.43
    পার
    0.42
    Activations Density 0.000%

    No Known Activations