© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28865
    Prev
    Next
    INDEX
    Explanations

    energetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     superlative
    0.41
     Questi
    0.38
     Ψ
    0.38
     verstehen
    0.37
    elser
    0.37
     logical
    0.36
     नंबर्स
    0.36
    avate
    0.36
     理解
    0.36
    ண்மை
    0.36
    POSITIVE LOGITS
     accidentally
    0.40
    Puerto
    0.40
    姑娘
    0.38
    ᱞ
    0.38
     adored
    0.37
    Sin
    0.37
    신
    0.37
     ম
    0.36
     zuten
    0.36
     дево
    0.35
    Activations Density 0.067%

    No Known Activations