© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168691
    Prev
    Next
    INDEX
    Explanations

    dualism, reference letters, biblical figures, running business

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

    depends on, if you, whether you

    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
    Not in Any Lists

    No Comments

    Negative Logits
    èche
    0.47
    தற்கு
    0.44
     가능하다
    0.43
     전혀
    0.43
    ᄄ
    0.43
    ería
    0.42
    드의
    0.42
    eria
    0.42
    티
    0.41
    figure
    0.41
    POSITIVE LOGITS
     jails
    0.56
     прове
    0.54
     apps
    0.52
     Arbeits
    0.51
     opi
    0.51
    1
    0.51
     SR
    0.51
     Prac
    0.51
     psi
    0.50
     deserts
    0.50
    Activations Density 0.000%

    No Known Activations