© 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. 17601
    Prev
    Next
    INDEX
    Explanations

    numbers and biblical references

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

    binary addition of bits

    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
     TOL
    0.47
     پک
    0.44
     przest
    0.43
     EnglishChoose
    0.42
    ihuahua
    0.42
     डिट
    0.42
     തെ
    0.41
    ϑ
    0.41
    creativecommons
    0.41
    tablename
    0.41
    POSITIVE LOGITS
     levied
    0.41
    合作
    0.39
     unparalleled
    0.38
    Gary
    0.38
     competición
    0.37
     competition
    0.37
     تعاون
    0.37
    competition
    0.36
    лете
    0.36
     lingered
    0.36
    Activations Density 0.007%

    No Known Activations