© 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. 203823
    Prev
    Next
    INDEX
    Explanations

    missional movements, National Trust, private pools

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

    influencing policy, treated like, reveal information

    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
    ();
    0.49
    Saharan
    0.48
     유지
    0.48
    Literatura
    0.47
     renov
    0.46
    言
    0.46
    zentration
    0.45
    前的
    0.45
     etab
    0.45
    도
    0.45
    POSITIVE LOGITS
     magically
    0.48
     phóng
    0.48
     Фургала
    0.45
     yao
    0.45
     گراف
    0.44
     graphically
    0.44
    yah
    0.43
     Yao
    0.43
     phẳng
    0.42
    ونکی
    0.41
    Activations Density 0.000%

    No Known Activations