© 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. 23819
    Prev
    Next
    INDEX
    Explanations

    long way to go

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

    This neuron detects variants of the expression indicating there’s more progress needed—i.e. “still have a long way to go” and similar phrases.

    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
     elég
    -0.91
    Válasz
    -0.91
     zask
    -0.90
    lında
    -0.89
    вот
    -0.89
     beginnt
    -0.85
     akár
    -0.85
     antecedentes
    -0.84
    怀里
    -0.83
    redor
    -0.83
    POSITIVE LOGITS
     work
    2.09
    まだまだ
    1.89
     still
    1.59
     ainda
    1.51
     jeszcze
    1.45
     ještě
    1.45
     much
    1.41
     ešte
    1.41
    work
    1.38
     improvements
    1.38
    Activations Density 0.030%

    No Known Activations