© 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. 57997
    Prev
    Next
    INDEX
    Explanations

    if...then statements

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

    contextual questions, Local Facebook

    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
     mối
    0.53
    不可以
    0.48
     نفس
    0.47
     وقد
    0.45
    欣
    0.45
     метро
    0.45
    هش
    0.44
    زة
    0.43
    smoothed
    0.43
    س
    0.43
    POSITIVE LOGITS
    li
    0.54
     Theories
    0.50
    ler
    0.49
    cer
    0.49
    ujan
    0.48
    _',
    0.47
     theories
    0.47
    ls
    0.47
     semua
    0.46
    iti
    0.46
    Activations Density 0.000%

    No Known Activations