© 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. 220165
    Prev
    Next
    INDEX
    Explanations

    numbers and benefit plans

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

    use simple social terms

    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
     ジャン
    0.51
     झा
    0.49
     봐
    0.46
     결과를
    0.44
     했다
    0.44
    sement
    0.44
     मार्ग
    0.44
     통해서
    0.43
     ಆರೋಗ್ಯ
    0.43
    alignParentRight
    0.43
    POSITIVE LOGITS
    ந்திய
    0.52
    ν
    0.50
     frein
    0.47
    ന
    0.47
     accum
    0.46
     amass
    0.46
    Percentage
    0.45
    ζ
    0.45
    Theo
    0.45
     perceiving
    0.44
    Activations Density 0.001%

    No Known Activations