© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14737
    Prev
    Next
    INDEX
    Explanations

    locations and positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     các
    0.51
     diversión
    0.50
    мерикан
    0.50
     rozší
    0.49
     contiene
    0.49
    Tenemos
    0.49
     delirium
    0.49
    뵌
    0.48
     contienen
    0.48
    অর্চনা
    0.48
    POSITIVE LOGITS
     location
    1.19
    位置
    1.19
     위치
    1.18
     Location
    1.16
    location
    1.15
     position
    1.13
    Location
    1.12
     posizione
    1.12
     posição
    1.12
     Position
    1.11
    Activations Density 0.195%

    No Known Activations