© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3644
    Prev
    Next
    INDEX
    Explanations

    keep / kept / keeps / keeping

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

    keeping or maintaining

    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_53_width_65k_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
     साहस
    0.39
    鑊
    0.38
     опо
    0.36
    цом
    0.35
     نروح
    0.34
    సరం
    0.33
    毫无
    0.33
     प्रस
    0.33
    خبر
    0.33
    遑
    0.33
    POSITIVE LOGITS
    keep
    4.50
     keep
    4.41
    Keep
    4.41
     Keep
    4.38
     KEEP
    4.31
    KEEP
    4.06
     keeping
    4.00
     keeps
    4.00
     kept
    3.86
    keeps
    3.84
    Activations Density 0.438%

    No Known Activations