© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144206
    Prev
    Next
    INDEX
    Explanations

    leading to or following certain words

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

    safeguards and why they are imperfect

    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
    Negative Logits
    enças
    0.56
    ResBuffer
    0.50
     жүктөө
    0.48
     गुस्सा
    0.48
    CHREIB
    0.47
    Mâc
    0.45
    ُمْ
    0.45
     quirúrg
    0.45
    ाल
    0.44
     መጨ
    0.44
    POSITIVE LOGITS
     {
    0.48
    ,
    0.48
     its
    0.48
     >
    0.46
     you
    0.46
    <eos>
    0.46
    0.44
     itself
    0.43
     both
    0.42
     <
    0.42
    Activations Density 0.000%

    No Known Activations