© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7120
    Prev
    Next
    INDEX
    Explanations

    prepositions of location

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

    spatial relationships and objects

    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_53_width_65k_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
    訶
    0.42
    年始
    0.41
     снаб
    0.40
     povol
    0.39
    닮
    0.38
    シンプルな
    0.38
     compartmental
    0.37
    鮎
    0.37
    ＂
    0.36
    renc
    0.36
    POSITIVE LOGITS
     windowsill
    1.01
     railings
    0.98
     bushes
    0.94
     trees
    0.94
     دیوار
    0.92
     railing
    0.89
    桌
    0.86
     desks
    0.84
     테이블
    0.82
    trees
    0.82
    Activations Density 0.206%

    No Known Activations