© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109916
    Prev
    Next
    INDEX
    Explanations

    Gemma Activation Bonding Cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     over
    0.54
     över
    0.49
    ;;)
    0.45
     omkring
    0.44
     \&
    0.42
     entre
    0.42
     whiskey
    0.42
     !$
    0.42
     een
    0.41
     både
    0.41
    POSITIVE LOGITS
    ᱘
    0.52
    ﺔ
    0.51
    iftoire
    0.50
    avad
    0.49
    ຢ
    0.48
    urally
    0.46
    ஆக
    0.46
     रिले
    0.46
     சுற்று
    0.46
    ərə
    0.45
    Activations Density 0.003%

    No Known Activations