© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82922
    Prev
    Next
    INDEX
    Explanations

    towards specific goals

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

    The neuron is primarily detecting English words with common inflectional endings (-ed, ‑ing, or plural ‑s).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دست
    -0.91
     conosce
    -0.77
    உ
    -0.75
    iausi
    -0.75
    اخ
    -0.75
     ajutor
    -0.75
    Through
    -0.74
     飲み
    -0.73
    Donnerstag
    -0.73
    さんと
    -0.72
    POSITIVE LOGITS
     towards
    8.31
     toward
    7.53
    towards
    6.00
     Towards
    5.53
    Towards
    5.47
    toward
    5.34
     Toward
    5.09
     hacia
    5.06
    Toward
    5.00
     TOW
    3.22
    Activations Density 0.279%

    No Known Activations