© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55505
    Prev
    Next
    INDEX
    Explanations

    find documents

    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_65k_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
     съем
    0.44
    м
    0.41
     σύν
    0.40
    霝
    0.40
     엄
    0.39
    菪
    0.39
     других
    0.39
     деся
    0.39
     інших
    0.39
    땃
    0.39
    POSITIVE LOGITS
     wildflowers
    0.38
    🫦
    0.38
     Fron
    0.38
     porté
    0.37
    円
    0.37
    
    0.37
     Therefore
    0.36
     done
    0.35
    chief
    0.35
     aimed
    0.35
    Activations Density 0.002%

    No Known Activations