© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17427
    Prev
    Next
    INDEX
    Explanations

    vanity mirror

    np_acts-logits-general · gemini-2.5-flash-lite

    mirror mirror on the wall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     заяв
    0.49
     مها
    0.42
     санк
    0.41
    zés
    0.39
    friends
    0.39
     Amnesty
    0.39
     migrants
    0.38
    굼
    0.38
     incarcer
    0.37
    adek
    0.37
    POSITIVE LOGITS
     mirror
    1.35
     Mirror
    1.34
    Mirror
    1.27
    鏡
    1.27
     mirrors
    1.23
     зерка
    1.23
    镜
    1.21
     Mirrors
    1.20
    mirror
    1.18
     दर्पण
    1.09
    Activations Density 0.056%

    No Known Activations