© 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. 157449
    Prev
    Next
    INDEX
    Explanations

    Fraser R pension monthly rotation

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

    what is currently happening

    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
     Elektrokh
    0.51
     آش
    0.50
    ა
    0.50
    놨
    0.47
    zneim
    0.47
    WORKDIR
    0.47
    യായ
    0.46
    鸷
    0.46
     Subsect
    0.45
     İlç
    0.45
    POSITIVE LOGITS
    more
    0.50
    law
    0.49
     This
    0.48
    this
    0.47
     heute
    0.46
     continuity
    0.45
     democratic
    0.45
     invest
    0.45
     oggi
    0.45
     هذه
    0.43
    Activations Density 0.000%

    No Known Activations