© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116449
    Prev
    Next
    INDEX
    Explanations

    research and development terms

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

    The neuron detects long abstract nominalizations—content words ending in suffixes like ‑ion, ‑ment, ‑al, etc.

    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
    точка
    -1.20
    にします
    -1.01
     carregar
    -0.98
    ސ
    -0.93
    ousine
    -0.91
    ということです
    -0.91
    我只是
    -0.90
    minimal
    -0.90
     inkább
    -0.89
    ライム
    -0.87
    POSITIVE LOGITS
     and
    2.77
     of
    2.63
     וה
    1.15
    жность
    1.06
     وت
    0.99
     certain
    0.98
    ność
    0.93
     ?</
    0.91
    kalender
    0.90
    }?
    0.90
    Activations Density 0.223%

    No Known Activations