© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11692
    Prev
    Next
    INDEX
    Explanations

    location and description

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

    The neuron fires on salient content nouns – in particular, the head noun in a descriptive noun phrase.

    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_31_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
    ிறது
    0.59
     Tand
    0.58
     Its
    0.55
     imaginary
    0.52
     unmittelbar
    0.52
     Vereinigte
    0.52
    ార్
    0.52
    இந்நிலையில்
    0.51
     Esta
    0.51
     radial
    0.51
    POSITIVE LOGITS
     거기
    0.80
     acolo
    0.77
     там
    0.72
     there
    0.71
     него
    0.71
     ahí
    0.69
     거기에
    0.69
    there
    0.66
     людей
    0.62
    そこ
    0.61
    Activations Density 0.193%

    No Known Activations