© 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. 3386
    Prev
    Next
    INDEX
    Explanations

    long-term

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

    long-term outcomes and goals

    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
    kirche
    0.52
    ați
    0.52
     Каждый
    0.51
    codec
    0.50
    ה
    0.50
    再
    0.50
    َّ
    0.48
    SubDirectoryPath
    0.48
     Кра
    0.47
     conoscere
    0.46
    POSITIVE LOGITS
     longterm
    0.74
    အတွက်
    0.61
     advertis
    0.59
     लॉन्ग
    0.59
    長期
    0.57
     (>
    0.56
    LONG
    0.55
     दीर्घ
    0.54
     alternativa
    0.53
     abstinence
    0.53
    Activations Density 0.031%

    No Known Activations