© 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. 10932
    Prev
    Next
    INDEX
    Explanations

    spatial terms following 'the'

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

    locations or surfaces

    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
    ēl
    0.37
    các
    0.37
     assunto
    0.36
     фаразы
    0.35
    Კ
    0.35
     कॉनक
    0.34
    assignmentItems
    0.34
     মর্যা
    0.34
     את
    0.33
    സ്തു
    0.33
    POSITIVE LOGITS
     periphery
    0.39
     outskirts
    0.38
     floor
    0.35
     front
    0.34
     verge
    0.32
     sidelines
    0.32
     f
    0.32
     temple
    0.32
     very
    0.32
     altar
    0.31
    Activations Density 0.312%

    No Known Activations