© 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. 10-GEMMASCOPE-RES-131K
    7. 39349
    Prev
    Next
    INDEX
    Explanations

    statements about status so far

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

    This neuron detects occurrences of the word “far,” as in the common discourse marker “so far.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    盍
    -2.06
    靫
    -2.05
     cansado
    -2.03
     zijne
    -2.02
     jesús
    -2.00
    )　
    -1.98
     奶茶
    -1.97
    りは
    -1.97
    嶠
    -1.97
     niños
    -1.96
    POSITIVE LOGITS
    u
    2.55
    ’
    2.53
    )
    2.36
     selben
    2.27
    ”
    2.23
    “
    2.22
     einige
    2.14
     wenige
    2.14
    ta
    2.09
    ing
    2.03
    Activations Density 0.005%

    No Known Activations