© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2893
    Prev
    Next
    INDEX
    Explanations

    heels

    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_16_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
    恙
    0.59
    ッテリー
    0.54
    мий
    0.51
    etchup
    0.50
    க்கு
    0.50
    ussian
    0.50
    τ
    0.50
    erving
    0.49
     térmica
    0.47
    itness
    0.47
    POSITIVE LOGITS
     sandals
    0.89
     Shoes
    0.88
     Shoe
    0.87
     shoes
    0.86
    鞋
    0.82
     靴
    0.77
     shoe
    0.76
    Shoes
    0.75
    shoes
    0.73
     zapatos
    0.71
    Activations Density 0.008%

    No Known Activations