© 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. 199475
    Prev
    Next
    INDEX
    Explanations

    sustainable development

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

    creative attributes and abstract ideas

    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
    רה
    0.57
    בי
    0.52
    αρ
    0.52
    ק
    0.49
    สัง
    0.47
    Ϲ
    0.47
    Roi
    0.46
    ወ
    0.46
    ראל
    0.45
    ס
    0.45
    POSITIVE LOGITS
     Sustainable
    0.55
     sustainability
    0.55
     sustainable
    0.51
     معانا
    0.48
     disruption
    0.47
     Sustain
    0.46
     advocacy
    0.46
     sostenibilidad
    0.45
     environmental
    0.45
    知的
    0.44
    Activations Density 0.002%

    No Known Activations