© 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. 57330
    Prev
    Next
    INDEX
    Explanations

    possession and existence in multiple languages

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

    ethical and qualitative judgments

    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
    টল
    0.41
    gelopen
    0.38
    藹
    0.35
     allies
    0.35
     hey
    0.34
     Aren
    0.34
     ML
    0.34
     सकेगा
    0.34
    렐
    0.34
     populations
    0.34
    POSITIVE LOGITS
     να
    0.92
     أن
    0.67
     faptul
    0.63
     داشتن
    0.63
     having
    0.61
    こういう
    0.60
    avoir
    0.58
    ที่จะ
    0.56
     imati
    0.55
    having
    0.54
    Activations Density 0.127%

    No Known Activations