© 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. 55184
    Prev
    Next
    INDEX
    Explanations

    ordering or sequencing

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

    fear of abandonment

    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
     selbst
    0.44
     Bürgermeister
    0.44
     повністю
    0.44
    і
    0.43
     gór
    0.43
    дяки
    0.42
    زي
    0.42
     yüzden
    0.42
     Woche
    0.41
     dishon
    0.41
    POSITIVE LOGITS
     realms
    0.47
     믿
    0.46
     메시
    0.46
     틀
    0.45
    foundation
    0.45
     기반
    0.45
     기본적인
    0.44
     messages
    0.44
     idea
    0.44
     모델
    0.43
    Activations Density 0.000%

    No Known Activations