© 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. 112751
    Prev
    Next
    INDEX
    Explanations

    your body parts

    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
     Allows
    0.52
     eneste
    0.51
     टीवी
    0.51
     Использу
    0.50
    🛹
    0.50
     YouTuber
    0.49
     permite
    0.48
     Якщо
    0.48
     permitem
    0.46
     }}"
    0.46
    POSITIVE LOGITS
     harmonies
    0.49
     historians
    0.48
     architecture
    0.45
     epic
    0.45
     influence
    0.44
     masterful
    0.44
     다시
    0.42
     allegory
    0.42
     dominance
    0.42
     organes
    0.41
    Activations Density 0.008%

    No Known Activations