© 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. 9604
    Prev
    Next
    INDEX
    Explanations

    modify, distribute, or publish

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

    The neuron flags boilerplate copyright and reproduction-permission statements in legal/license texts.

    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
     कॉन्
    0.61
    ეგის
    0.61
     {@
    0.60
    LICENSE
    0.59
     procured
    0.56
     procedural
    0.56
     Legal
    0.55
     SHALL
    0.55
    แมนเชสเตอร์ซิตี
    0.55
     보호
    0.54
    POSITIVE LOGITS
     microfilm
    0.74
     photocopying
    0.63
    делать
    0.61
     photocopy
    0.61
    教
    0.56
     polynucle
    0.56
    isPlaying
    0.54
     biochemical
    0.54
    排出
    0.52
     преподава
    0.52
    Activations Density 0.095%

    No Known Activations