© 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. 210752
    Prev
    Next
    INDEX
    Explanations

    games, countries, dates

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

    specific routine, budget, scope, authority

    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
     Isle
    0.53
     user
    0.50
     kn
    0.49
    isle
    0.49
     stain
    0.49
     monochrom
    0.48
     o
    0.48
     u
    0.47
     histogram
    0.46
     lime
    0.46
    POSITIVE LOGITS
    ات
    0.61
    ت
    0.60
    جل
    0.59
    ك
    0.59
    عيد
    0.57
    م
    0.56
    حب
    0.55
    س
    0.55
    كار
    0.53
    زوج
    0.53
    Activations Density 0.000%

    No Known Activations