© 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. 7054
    Prev
    Next
    INDEX
    Explanations

    come a long way

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

    the idiomatic expression of significant progress, specifically “come a long way” or its variant “go a long way.”

    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
    nesting
    -0.83
    vám
    -0.80
    LETTERS
    -0.79
    nění
    -0.79
    BeNil
    -0.77
    ští
    -0.77
     RAIL
    -0.77
    ⿱
    -0.77
    juje
    -0.77
    atiques
    -0.76
    POSITIVE LOGITS
     long
    3.17
    long
    2.09
     LONG
    1.80
     longo
    1.71
    Long
    1.71
     a
    1.70
     ways
    1.70
     Long
    1.57
     долго
    1.53
    LONG
    1.48
    Activations Density 0.016%

    No Known Activations