© 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. 65159
    Prev
    Next
    INDEX
    Explanations

    use their

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

    engine oil, angry violence, frantically search, Top of Rock, photosphere, slug

    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
     garment
    0.57
    Date
    0.47
    Philippines
    0.47
     locations
    0.46
     garments
    0.45
    Creator
    0.44
     ship
    0.44
     \
    0.43
     surveyor
    0.42
    NHS
    0.42
    POSITIVE LOGITS
     這個
    0.59
     WHICH
    0.56
    사를
    0.54
    지만
    0.53
     並
    0.53
     každ
    0.52
    每一個
    0.52
     중에
    0.51
     Trabalho
    0.51
     каждой
    0.50
    Activations Density 0.000%

    No Known Activations