© 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. 201173
    Prev
    Next
    INDEX
    Explanations

    religious affiliations and medical reasons

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

    Test scenarios

    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
    t
    0.55
    c
    0.52
    l
    0.47
    lare
    0.44
    will
    0.44
    捛
    0.42
    be
    0.42
    WILL
    0.42
    ]?.
    0.41
    езд
    0.41
    POSITIVE LOGITS
     یاد
    0.49
    ılan
    0.48
     Gem
    0.47
     Agama
    0.47
     Acest
    0.47
    ˮ
    0.47
    枞
    0.46
     Deli
    0.46
     sermons
    0.45
    庚
    0.45
    Activations Density 0.001%

    No Known Activations