© 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. 208792
    Prev
    Next
    INDEX
    Explanations

    in condition or appearance

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

    Holocaust, Core, mnist

    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
     ప్రశ్
    0.47
     específicamente
    0.46
    verbosity
    0.46
    #############
    0.46
    uyết
    0.43
    өрү
    0.43
    🚈
    0.43
     বক্তব্যে
    0.42
    ismatch
    0.42
    🏪
    0.41
    POSITIVE LOGITS
     earthly
    0.53
     Kri
    0.52
     wooden
    0.51
     einem
    0.49
     stalks
    0.49
     otherworldly
    0.49
     charcoal
    0.49
     vases
    0.48
     Chama
    0.48
     abode
    0.47
    Activations Density 0.003%

    No Known Activations