© 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. 60503
    Prev
    Next
    INDEX
    Explanations

    in writing

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

    The neuron flags multi-word “canned” or boilerplate expressions (e.g. fixed idiomatic sequences like “lack of a better word” or “agreed to in writing”).

    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
     לפי
    -0.84
     Sees
    -0.71
    loroethane
    -0.71
    ecore
    -0.69
     skor
    -0.68
    ช
    -0.67
    tapi
    -0.67
    athan
    -0.67
     itd
    -0.66
    𝚝
    -0.66
    POSITIVE LOGITS
     RNG
    0.67
    şte
    0.66
    melis
    0.65
    RNG
    0.64
    cog
    0.63
     sucedido
    0.63
     الاص
    0.62
    Lev
    0.62
    ператор
    0.61
    DMC
    0.61
    Activations Density 0.079%

    No Known Activations