© 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. 1744
    Prev
    Next
    INDEX
    Explanations

    your/a/his/my + noun/adjective

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

    This neuron strongly activates on low-frequency (i.e. uncommon or rare) tokens.

    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
    ہ
    0.56
    ਲੀ
    0.55
    venido
    0.52
     espaces
    0.52
    ర్
    0.50
    ljed
    0.50
    antoms
    0.50
     ihe
    0.48
     dampers
    0.48
     workspaces
    0.48
    POSITIVE LOGITS
    。
    0.57
    )
    0.46
    .
    0.44
    ?
    0.43
    ㅏ
    0.43
     製
    0.42
    }
    0.42
    ↵↵
    0.41
     влия
    0.41
    ).
    0.41
    Activations Density 0.000%

    No Known Activations