© 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. 6667
    Prev
    Next
    INDEX
    Explanations

    meaning or

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

    This neuron detects words referring to visual scenes or scenery (e.g., “scenery,” “view,” “scene,” “landscape,” or equivalent terms).

    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
     S
    0.80
     जरी
    0.71
     ከ
    0.70
    S
    0.70
    K
    0.70
     sizlere
    0.69
    Minimum
    0.68
     FIVE
    0.68
     AND
    0.68
    Jika
    0.68
    POSITIVE LOGITS
     или
    1.06
     разнови
    1.02
     oneself
    0.97
     또는
    0.96
     או
    0.94
     அல்லது
    0.93
     یا
    0.92
     或
    0.92
    或
    0.92
     หรือ
    0.91
    Activations Density 0.123%

    No Known Activations