© 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. 9593
    Prev
    Next
    INDEX
    Explanations

    screen modes

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

    The neuron activates on mentions of full-screen viewing or toggling into full-screen mode.

    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
     visant
    0.61
    Cmd
    0.59
     miles
    0.57
    ArgsEnv
    0.55
    緒
    0.55
    miles
    0.55
     direita
    0.55
    ধ্বনি
    0.55
    voerd
    0.55
     mile
    0.54
    POSITIVE LOGITS
     풀
    0.59
     Belly
    0.51
     उपासना
    0.49
     Mailing
    0.49
     reconstruction
    0.48
     lum
    0.48
     GERM
    0.48
    낍
    0.48
     인수
    0.48
    mino
    0.48
    Activations Density 0.000%

    No Known Activations