© 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. 9287
    Prev
    Next
    INDEX
    Explanations

    Japan surrendered

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

    The neuron is essentially responding to the length of a text segment, activating more strongly on longer passages.

    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
    Away
    0.59
    ↓↓
    0.58
    Посилання
    0.55
    ◥
    0.55
    xception
    0.54
    "/>
    0.54
     escapar
    0.53
    кож
    0.51
     근
    0.51
    ↕
    0.50
    POSITIVE LOGITS
     деле
    0.52
     verification
    0.50
     Swan
    0.50
    जून
    0.50
     faith
    0.49
     anti
    0.48
     swans
    0.48
     &_
    0.48
     fraud
    0.48
    jacking
    0.48
    Activations Density 0.005%

    No Known Activations