© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8393
    Prev
    Next
    INDEX
    Explanations

    explaining similarities and differences

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

    The neuron flags exhortative or reflective action words—especially verbs issuing instructions or calls to think/consider (e.g. “think,” “remember,” “reap,” “volunteer”).

    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
    】,
    0.68
     څخه
    0.63
    czeniu
    0.63
    ᾷ
    0.62
     તેમજ
    0.61
     emeritus
    0.59
    बाबत
    0.59
    ayin
    0.59
    琬
    0.59
    ifred
    0.59
    POSITIVE LOGITS
     ebenso
    0.56
    、
    0.53
     correspondingly
    0.53
     كذلك
    0.53
    、（
    0.50
     sebagainya
    0.48
     Likewise
    0.48
     equally
    0.47
     এটাও
    0.47
     dunque
    0.47
    Activations Density 0.879%

    No Known Activations