© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35210
    Prev
    Next
    INDEX
    Explanations

    introducing a point of view

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

    This neuron detects the phrase pattern “from a/an … standpoint.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    などに
    -1.46
    などは
    -1.33
    などを
    -1.29
    など
    -1.26
    aneity
    -1.21
    などなど
    -1.15
    などの
    -1.15
    bộ
    -1.11
     són
    -1.11
    cómo
    -1.09
    POSITIVE LOGITS
    HasBeenSet
    1.22
    利的
    1.20
     consumers
    1.20
     -
    1.09
     marketing
    1.08
     theoretical
    1.06
     perspective
    1.06
    ttf
    1.05
     consumer
    1.02
     logistics
    1.01
    Activations Density 0.016%

    No Known Activations