© 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. 83752
    Prev
    Next
    INDEX
    Explanations

    no point or need

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

    The neuron strongly triggers on question-opening phrasing, in particular the “What is the …” (e.g. “What is the point of”) pattern.

    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
    ikawa
    -0.82
    OLUTION
    -0.81
    liğ
    -0.81
    ))=\
    -0.77
    ieš
    -0.77
    
    -0.75
     آرز
    -0.73
    autique
    -0.73
     gejala
    -0.73
    潢
    -0.73
    POSITIVE LOGITS
     point
    3.97
    point
    3.00
    Point
    2.69
     Point
    2.58
     purpose
    2.58
     POINT
    2.34
    POINT
    2.33
     pointless
    2.06
     punto
    2.03
     benefit
    1.79
    Activations Density 0.027%

    No Known Activations