© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3971
    Prev
    Next
    INDEX
    Explanations

    s

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

    This neuron detects the genitive ’s suffix on proper nouns, marking possession or attribution.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
     의견
    0.70
    🦵
    0.70
     그림
    0.68
     책
    0.68
     ώ
    0.67
    ПР
    0.67
     위의
    0.66
    가의
    0.65
     인생
    0.65
     которое
    0.63
    POSITIVE LOGITS
     sogenannten
    0.88
     sogenannte
    0.82
     monarchy
    0.78
     notorious
    0.78
     Ministry
    0.77
     vrije
    0.76
    लिये
    0.76
     Transportation
    0.75
     Finest
    0.75
     multimillion
    0.75
    Activations Density 0.048%

    No Known Activations