© 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. 5509
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

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

    acronyms starting with single letters

    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
     ignoreString
    0.28
     GoObject
    0.27
    ྪ
    0.27
     ascend
    0.26
     angrily
    0.26
     resTmp
    0.25
     넣
    0.25
     awkwardly
    0.25
    ভিয়েতনাম
    0.25
    ྜ
    0.25
    POSITIVE LOGITS
    -
    0.34
    i
    0.31
    ie
    0.28
    ’
    0.27
     T
    0.24
     U
    0.24
    ‑
    0.24
    ia
    0.24
    mathbf
    0.23
    <strong>
    0.23
    Activations Density 0.559%

    No Known Activations