© 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. 15192
    Prev
    Next
    INDEX
    Explanations

    capital cities and countries

    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
    傈
    0.57
    PropertySheets
    0.48
    ARTER
    0.46
     Ł
    0.46
    逦
    0.46
     일반
    0.45
     سریال
    0.44
    ইডি
    0.44
    AGENT
    0.43
     组件
    0.43
    POSITIVE LOGITS
     anticipated
    0.52
    anticipated
    0.45
     memor
    0.44
     must
    0.43
     unnecessary
    0.43
     tooth
    0.42
     superfluous
    0.42
     emeritus
    0.42
     strenuous
    0.42
    ስ
    0.41
    Activations Density 0.011%

    No Known Activations