© 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. 48257
    Prev
    Next
    INDEX
    Explanations

    for you / your

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

    This neuron detects recommendation or suitability phrases phrased as “X for you,” e.g. “right for you,” “best for you,” or “works for you.”

    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
    bandcamp
    -0.97
     anything
    -0.92
    Anything
    -0.90
    šky
    -0.88
    寕
    -0.88
    Same
    -0.87
    ()])
    -0.86
    SAME
    -0.85
    opie
    -0.85
    Anyone
    -0.84
    POSITIVE LOGITS
     situation
    1.55
     your
    1.50
     particular
    1.38
     needs
    1.29
     YOUR
    1.27
     circumstances
    1.27
     him
    1.22
     конкре
    1.13
     given
    1.12
    Situation
    1.09
    Activations Density 0.039%

    No Known Activations