© 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. 201803
    Prev
    Next
    INDEX
    Explanations

    wife, mother, WiFi, salt

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

    synthetic leather or willpower

    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
    佲
    0.58
    古代
    0.54
    れない
    0.54
    ሀ
    0.52
    庤
    0.51
    نہ
    0.51
    だけの
    0.49
    ဆင့်
    0.49
    ྗ
    0.49
    дження
    0.48
    POSITIVE LOGITS
     that
    0.49
     prote
    0.47
     las
    0.47
     atu
    0.47
     ud
    0.46
     NF
    0.46
     Worldwide
    0.46
    lds
    0.46
     fluid
    0.46
    0.45
    Activations Density 0.000%

    No Known Activations