© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15331
    Prev
    Next
    INDEX
    Explanations

    circular solar halos

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

    This neuron picks out relatively uncommon, content‐bearing words (nouns or adjectives) rather than common function words.

    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
    ко
    0.87
    ী
    0.85
    l
    0.84
    к
    0.79
     vett
    0.78
    ﻛ
    0.77
     của
    0.76
    ahh
    0.75
     beautiful
    0.75
     planer
    0.73
    POSITIVE LOGITS
    DirPath
    0.85
    enediamine
    0.72
    MATERIALS
    0.71
     परीक्षाएं
    0.70
    cerpt
    0.70
    舛
    0.70
     Ketika
    0.69
    ists
    0.68
    TER
    0.68
    dims
    0.68
    Activations Density 0.000%

    No Known Activations