© 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. 163070
    Prev
    Next
    INDEX
    Explanations

    word sequences

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

    online safety, outstanding mortgage, resilience

    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
    و
    0.49
    Prox
    0.47
    1
    0.45
    пси
    0.45
    u
    0.43
    ゆ
    0.43
    ui
    0.42
    ਗ
    0.42
    ו
    0.41
    us
    0.41
    POSITIVE LOGITS
     TouchUtils
    0.51
    পূর্ণ
    0.49
     শক্তিশালী
    0.45
     المغرب
    0.44
    AssetsRequest
    0.43
    পূর্ন
    0.43
    ({\
    0.42
     హై
    0.42
     পূর্ণ
    0.40
    ceso
    0.40
    Activations Density 0.001%

    No Known Activations