© 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. 145746
    Prev
    Next
    INDEX
    Explanations

    technical context or meta-language indicators

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

    deliberate conditional phrasing

    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
    мери
    0.49
    спекти
    0.49
     еще
    0.47
     briefly
    0.46
     tirelessly
    0.46
     retailing
    0.44
    ጢ
    0.44
     clumsy
    0.44
    ред
    0.43
     intently
    0.43
    POSITIVE LOGITS
     条件
    0.46
    减
    0.43
     ecc
    0.43
    institution
    0.43
    centos
    0.42
     عدم
    0.41
    SdkVersion
    0.41
    しよう
    0.40
    ：（
    0.40
     recue
    0.40
    Activations Density 0.000%

    No Known Activations